INDEX

Explanations

conjunctions and discussions related to conditions and factors 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 @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

onte

-0.18

aur

-0.17

icari

-0.15

æīį

-0.15

oods

-0.14

 acids

-0.13

afi

-0.13

">ÃĹ</

-0.13

cab

-0.13

POSITIVE LOGITS

 _______,

0.19

ROKE

0.15

inel

0.15

HITE

0.15

 ,č↵

0.14

Sensitive

0.14

ì²Ļ

0.14

 varsa

0.13

NODE

0.13

cies

0.13

Activations Density 0.160%

conjunctions and discussions related to conditions and factors in various contexts

No Comments

No Known Activations