INDEX

Explanations

names and identifiers related to locations and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

IODevice

-0.14

odv

-0.14

Ã¢k

-0.13

abcdefghijklmnop

-0.13

IGHLIGHT

-0.13

oruÄį

-0.12

/question

-0.12

 okol

-0.12

Î³Î³ÎµÎ»

-0.12

ALSE

-0.12

POSITIVE LOGITS

 âĢ¦↵

0.14

âĢ¦↵

0.13

 “âĢ¦

0.12

 âĸł

0.12

 âĸº

0.12

’

0.12

Äį

0.12

 Ekon

0.11

affles

0.11

Activations Density 1.716%

names and identifiers related to locations and organizations

No Comments

No Known Activations