INDEX

Explanations

references to prominent individuals and their roles or contributions in various contexts

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

Å¡ov

-0.17

raphics

-0.15

tring

-0.15

Ð°Ð½ÑĤÐ°

-0.15

-Sah

-0.14

igy

-0.14

à¸Ļà¸²à¸¢

-0.13

åĩ¡

-0.13

logan

-0.13

ÑĢÐµÑĪ

-0.13

POSITIVE LOGITS

 talk

0.42

 discuss

0.40

 talks

0.38

 discusses

0.36

 talking

0.36

 talked

0.35

 discussing

0.35

talk

0.33

è°Ī

0.31

 discussion

0.30

Activations Density 0.174%

references to prominent individuals and their roles or contributions in various contexts

No Comments

No Known Activations