INDEX

Explanations

phrases related to importance and significant roles 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 @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

rear

-0.18

rak

-0.17

Uvs

-0.16

abus

-0.15

rac

-0.15

ratings

-0.15

nodoc

-0.15

Routing

-0.15

Ð¾Ð³Ð¾Ð´

-0.15

Rek

-0.15

POSITIVE LOGITS

 role

0.72

 Role

0.59

role

0.56

 roles

0.56

-role

0.52

Role

0.51

_role

0.48

 ROLE

0.46

.role

0.45

 ÑĢÐ¾Ð»ÑĮ

0.45

Activations Density 0.090%

phrases related to importance and significant roles in various contexts

No Comments

No Known Activations