INDEX

Explanations

references to norm or standard practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

emer

-0.17

isci

-0.17

inke

-0.15

inel

-0.15

licken

-0.14

/tab

-0.14

reas

-0.14

lycer

-0.14

elig

-0.14

rÃ¡

-0.14

POSITIVE LOGITS

afa

0.17

ulin

0.17

ities

0.16

 Monk

0.16

arend

0.15

 suspects

0.15

pecting

0.14

oints

0.14

oint

0.14

mente

0.14

Activations Density 0.022%

references to norm or standard practices

No Comments

No Known Activations