INDEX

Explanations

disclaimers regarding legal and medical advice

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ubar

-0.15

Exist

-0.14

pread

-0.14

EXIST

-0.14

isky

-0.14

nett

-0.13

 Stevenson

-0.13

ropic

-0.13

 spoiled

-0.13

urch

-0.13

POSITIVE LOGITS

 endorsement

0.26

 endorse

0.25

 endorsed

0.23

 endorsements

0.23

 exhaustive

0.21

 endors

0.20

endor

0.19

 guarantee

0.19

 endorsing

0.19

 intended

0.19

Activations Density 0.074%

disclaimers regarding legal and medical advice

No Comments

No Known Activations