INDEX

Explanations

words related to advertising and branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

pte

-0.17

ena

-0.16

Ãªt

-0.14

 paddingRight

-0.14

ats

-0.14

inode

-0.14

cha

-0.14

 nowhere

-0.14

çľ

-0.14

HS

-0.14

POSITIVE LOGITS

udas

0.17

amik

0.17

flo

0.16

@student

0.16

illac

0.15

avax

0.15

oric

0.15

auss

0.15

ÏģÎ¿Ïį

0.14

ernes

0.14

Activations Density 0.287%

words related to advertising and branding

No Comments

No Known Activations