INDEX

Explanations

instances of specific punctuation or formatting in text

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

Ø¸Ùħ

-0.15

jÃŃm

-0.15

aal

-0.15

poÄį

-0.15

reck

-0.15

atsby

-0.15

ushing

-0.14

eting

-0.14

ÏĢÎµ

-0.14

BITS

-0.14

POSITIVE LOGITS

squ

0.17

squ

0.17

noun

0.17

uez

0.16

áº¯c

0.14

licable

0.14

Ã«n

0.14

Ð¼Ð¾ÑĤ

0.14

-t

0.13

 Benjamin

0.13

Activations Density 0.030%

instances of specific punctuation or formatting in text

No Comments

No Known Activations