INDEX

Explanations

phrases indicating actions or states of being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

utin

-0.14

emale

-0.14

ARG

-0.14

 grav

-0.13

instrument

-0.13

vie

-0.13

geo

-0.13

tridge

-0.13

 çŁ³

-0.13

POSITIVE LOGITS

antity

0.14

íĥĪ

0.14

Geh

0.14

é¨

0.14

GLOBALS

0.13

imum

0.13

antly

0.13

res

0.13

Ħ

0.13

Ã¶s

0.13

Activations Density 1.055%

phrases indicating actions or states of being

No Comments

No Known Activations