INDEX

Explanations

words related to restrictions or limitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

rei

-0.15

keit

-0.14

oli

-0.14

iry

-0.14

estre

-0.13

od

-0.13

_mgmt

-0.13

fried

-0.13

reau

-0.13

POSITIVE LOGITS

by

0.69

 oleh

0.56

 bá»Łi

0.51

 ØªÙĪØ³Ø·

0.47

by

0.46

_by

0.39

 Ø¨ÙĪØ§Ø³Ø·Ø©

0.36

 tarafÄ±ndan

0.35

.by

0.32

edBy

0.32

Activations Density 0.187%

words related to restrictions or limitations

No Comments

No Known Activations