INDEX

Explanations

phrases related to entertainment and popular culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

STS

-0.16

-0.15

 vidÃ©

-0.15

acker

-0.14

ader

-0.14

 Hubbard

-0.14

assen

-0.14

adele

-0.13

 DÃ¼n

-0.13

POSITIVE LOGITS

INED

0.16

aves

0.16

awks

0.15

ay

0.15

aset

0.14

bar

0.14

Tul

0.14

Kas

0.14

.synthetic

0.14

atics

0.14

Activations Density 0.143%

phrases related to entertainment and popular culture

No Comments

No Known Activations