INDEX

Explanations

terms related to collaboration or partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

raki

-0.18

istrat

-0.17

 chua

-0.15

edio

-0.15

ushima

-0.15

icina

-0.15

belongs

-0.14

Ð¼ÐµÑī

-0.14

ABA

-0.14

reu

-0.14

POSITIVE LOGITS

ings

0.18

essaging

0.16

fi

0.16

mo

0.16

int

0.15

fu

0.14

ma

0.14

mas

0.14

ga

0.14

 Wonderland

0.14

Activations Density 0.019%

terms related to collaboration or partnerships

No Comments

No Known Activations