INDEX

Explanations

phrases that indicate relationships or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

antt

-0.17

-0.14

arios

-0.14

trecht

-0.13

ttp

-0.13

auga

-0.13

íĺĳ

-0.13

æķ¦

-0.13

Ãºp

-0.13

 fitte

-0.13

POSITIVE LOGITS

Ì£

0.17

alto

0.17

tel

0.17

isto

0.16

Tob

0.15

 regards

0.15

 Kendall

0.14

tel

0.14

zan

0.14

Cad

0.13

Activations Density 0.091%

phrases that indicate relationships or comparisons

No Comments

No Known Activations