INDEX

Explanations

references to educational programs and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

INGER

-0.15

.googleapis

-0.15

ãĤ«ãĥĨ

-0.15

à¸Ļà¹Ģà¸ķ

-0.15

chter

-0.15

ÑĤÐ¾Ð³Ð¾

-0.15

DATES

-0.15

ynchronously

-0.14

.scalablytyped

-0.14

_PLATFORM

-0.14

POSITIVE LOGITS

,this

0.23

 ÙģØ¥ÙĨ

0.21

 this

0.20

this

0.19

 these

0.18

these

0.17

 ÑįÑĤÐ°

0.15

)this

0.15

uss

0.15

(this

0.15

Activations Density 0.332%

references to educational programs and initiatives

No Comments

No Known Activations