INDEX

Explanations

terms associated with achievement and success

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

 duty

-0.14

akin

-0.14

 Brow

-0.14

/web

-0.14

-Pack

-0.13

achen

-0.13

inder

-0.13

POSITIVE LOGITS

à¤¾à¤¯à¤ķ

0.17

asename

0.17

ffe

0.16

Ð´Ð°Ð¼

0.15

ystate

0.15

ahl

0.15

ÑħÐ°

0.15

///<

0.14

ationToken

0.14

ingly

0.14

Activations Density 0.102%

terms associated with achievement and success

No Comments

No Known Activations