INDEX

Explanations

specific numeric values and measurements related to instructions or guidelines

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ilen

-0.16

zure

-0.15

 QMap

-0.15

thur

-0.14

lash

-0.14

DMIN

-0.14

ASC

-0.14

ption

-0.14

switch

-0.14

POSITIVE LOGITS

çĸĨ

0.16

arie

0.16

bol

0.15

æĲ

0.14

enko

0.14

esium

0.14

 RuntimeObject

0.14

ACKET

0.14

ÑįÑĤÐ¾Ð¼Ñĥ

0.14

ç¿Ķ

0.14

Activations Density 4.503%

specific numeric values and measurements related to instructions or guidelines

No Comments

No Known Activations