INDEX

Explanations

references to historical events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Siege

-0.16

 siege

-0.15

CMD

-0.15

ihar

-0.15

aeda

-0.14

coeff

-0.14

SEG

-0.14

à¸ĵ

-0.14

bek

-0.14

CompleteListener

-0.14

POSITIVE LOGITS

imler

0.16

 neighbours

0.16

 Seas

0.15

 neighbour

0.15

 peace

0.14

unal

0.13

hed

0.13

 modern

0.13

uilder

0.13

inis

0.13

Activations Density 0.405%

references to historical events and their implications

No Comments

No Known Activations