INDEX

Explanations

references to media consumption and critique of information sources

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

"path

-0.15

prak

-0.15

 Mori

-0.15

ãģĭãģª

-0.14

airo

-0.14

ublish

-0.14

amat

-0.13

rys

-0.13

fon

-0.13

Aspect

-0.13

POSITIVE LOGITS

 magazines

0.19

 reading

0.19

 magazine

0.19

TV

0.17

 media

0.16

tv

0.16

heard

0.16

ighbours

0.16

 hearing

0.15

antz

0.15

Activations Density 0.151%

references to media consumption and critique of information sources

No Comments

No Known Activations