INDEX

Explanations

high-frequency conjunctions and common sentence structures in the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

igm

-0.15

anes

-0.15

ETY

-0.15

adratic

-0.15

 Quarry

-0.14

ude

-0.14

 deploy

-0.14

iers

-0.14

aders

-0.14

 quar

-0.13

POSITIVE LOGITS

iosa

0.15

edback

0.15

ctrine

0.14

prung

0.14

eree

0.14

 igen

0.14

chin

0.14

izin

0.14

TypeDef

0.14

ãĥĩãĤ£ãĤ¢

0.13

Activations Density 0.002%

high-frequency conjunctions and common sentence structures in the document

No Comments

No Known Activations