INDEX

Explanations

punctuation and conjunctions indicating connections in text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

taire

-0.14

.hxx

-0.14

clare

-0.14

æģµ

-0.14

 Outlook

-0.14

hti

-0.14

omid

-0.14

frey

-0.13

inou

-0.13

addir

-0.13

POSITIVE LOGITS

ãģ¤ãģ¶

0.17

ocop

0.17

LEC

0.17

escort

0.16

gig

0.15

ektÃ¶r

0.14

#-

0.14

ãĥ¼ãĤº

0.14

eneg

0.14

å¸Ŀ

0.14

Activations Density 0.471%

punctuation and conjunctions indicating connections in text

No Comments

No Known Activations