INDEX

Explanations

the word "it" across various contexts in the 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

onn

-0.15

qd

-0.14

ãģĹãģ¾

-0.14

à¸ªà¸ĸ

-0.14

rot

-0.13

 word

-0.13

acht

-0.13

 Recovery

-0.13

onium

-0.13

 recover

-0.13

POSITIVE LOGITS

Ð»Ð°Ð³Ð¾Ð´

0.16

Ãªu

0.15

imest

0.14

 Sanford

0.14

/mark

0.14

 Sorted

0.14

quire

0.14

CEPT

0.14

icens

0.14

 Dare

0.13

Activations Density 0.064%

the word "it" across various contexts in the text

No Comments

No Known Activations