INDEX

Explanations

expressions related to recurrence or repetition of actions and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 presently

-0.18

currently

-0.18

 currently

-0.17

 already

-0.17

already

-0.16

çĽ®åīį

-0.15

Ã£n

-0.15

ynamo

-0.15

agh

-0.15

 Ð½ÐµÐºÐ¾ÑĤÐ¾ÑĢ

-0.15

POSITIVE LOGITS

 never

0.33

 ever

0.33

 EVER

0.32

 Never

0.31

never

0.30

 NEVER

0.30

 jamais

0.29

Never

0.29

-ever

0.28

 anything

0.27

Activations Density 0.162%

expressions related to recurrence or repetition of actions and events

No Comments

No Known Activations