INDEX

Explanations

phrases indicating strong influences or commitments 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 oder

-0.15

 Ð¶Ðµ

-0.14

tti

-0.14

ëĭ´

-0.14

 somehow

-0.14

ptic

-0.14

wers

-0.13

ä¸ĬãģĮ

-0.13

agues

-0.13

vest

-0.13

POSITIVE LOGITS

_ioctl

0.18

ieder

0.17

 indeed

0.16

åĩĮ

0.14

ACHE

0.14

 parÃ§asÄ±

0.14

bole

0.13

emode

0.13

branch

0.13

Ø³ÙĪØ¨

0.13

Activations Density 0.711%

phrases indicating strong influences or commitments in various contexts

No Comments

No Known Activations