INDEX

Explanations

references to individuality and personalized attention

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

furt

-0.16

ibold

-0.15

ibilities

-0.15

fur

-0.15

 exited

-0.15

 Wasser

-0.15

 majority

-0.14

 hypotheses

-0.14

ayer

-0.14

patrick

-0.14

POSITIVE LOGITS

ized

0.18

swith

0.18

zed

0.17

/single

0.17

ity

0.17

/team

0.16

IZED

0.16

ately

0.16

itarian

0.15

olum

0.15

Activations Density 0.023%

references to individuality and personalized attention

No Comments

No Known Activations