INDEX

Explanations

mentions of entertainment

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

et

-0.14

@mail

-0.14

 Surveillance

-0.13

ujte

-0.13

irc

-0.13

MBED

-0.13

gut

-0.13

 Chapman

-0.13

etag

-0.13

POSITIVE LOGITS

itler

0.15

stitutions

0.14

familia

0.14

å¤ªéĥİ

0.14

wick

0.13

spb

0.13

lick

0.13

TX

0.13

fake

0.13

 settled

0.13

Activations Density 0.000%

mentions of entertainment

No Comments

No Known Activations