INDEX

Explanations

phrases indicating actions performed by something or someone

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ã¤r

-0.15

ih

-0.15

ezi

-0.14

ebo

-0.14

lesc

-0.14

eÄį

-0.14

DeltaTime

-0.14

æļ®

-0.14

arty

-0.14

ablish

-0.14

POSITIVE LOGITS

acz

0.15

ajar

0.15

anj

0.14

arness

0.14

cca

0.14

Stick

0.14

 repertoire

0.13

acob

0.13

 Optionally

0.13

Activations Density 0.020%

phrases indicating actions performed by something or someone

No Comments

No Known Activations