INDEX

Explanations

statements that highlight important facts and processes

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

alaria

-0.16

aler

-0.15

maz

-0.15

OfClass

-0.15

iete

-0.15

kil

-0.15

cente

-0.15

±

-0.15

Ŀi

-0.14

lington

-0.14

POSITIVE LOGITS

ems

0.17

aret

0.15

ion

0.15

end

0.15

eka

0.14

prus

0.14

Reader

0.14

hled

0.14

UA

0.14

ional

0.14

Activations Density 0.568%

statements that highlight important facts and processes

No Comments

No Known Activations