INDEX

Explanations

specific dates and times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Tyto

-0.16

etler

-0.16

-0.15

ropoda

-0.15

ATIO

-0.15

estre

-0.15

erset

-0.15

ulfilled

-0.14

uji

-0.14

POSITIVE LOGITS

forward

0.17

buc

0.16

zcze

0.16

ene

0.16

imes

0.16

 occasions

0.15

 Woods

0.15

ener

0.15

amine

0.15

enc

0.15

Activations Density 0.097%

specific dates and times

No Comments

No Known Activations