INDEX

Explanations

adverbs that describe the manner or quality of actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ushi

-0.15

ãģĵãĤį

-0.14

rename

-0.14

aret

-0.14

 Ð²Ð¾Ð²

-0.14

ted

-0.14

åı¸

-0.14

çĶļ

-0.14

apl

-0.14

YST

-0.13

POSITIVE LOGITS

 enough

0.25

mente

0.21

 Enough

0.17

acios

0.17

 máº½

0.16

ØŃØª

0.16

à¹Ĩ

0.16

wards

0.15

alli

0.15

/fast

0.15

Activations Density 0.253%

adverbs that describe the manner or quality of actions

No Comments

No Known Activations