INDEX

Explanations

phrases indicating transitions or conclusions related to time

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

à¤¿à¤

-0.15

ynch

-0.14

lbl

-0.14

ewis

-0.14

UPS

-0.14

 lore

-0.14

 ener

-0.14

ĵ°

-0.14

quin

-0.14

pedia

-0.14

POSITIVE LOGITS

of

0.18

/end

0.18

 stages

0.18

earing

0.16

Î´Î®

0.16

ifest

0.16

OfDay

0.15

 credits

0.15

Ã¡bado

0.15

/start

0.15

Activations Density 0.033%

phrases indicating transitions or conclusions related to time

No Comments

No Known Activations