INDEX

Explanations

references to URLs and file paths, particularly related to code repositories

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

iesta

-0.17

entine

-0.16

oric

-0.15

hma

-0.14

 McLaren

-0.14

ç±į

-0.14

erus

-0.14

oller

-0.14

 dump

-0.14

 lorem

-0.14

POSITIVE LOGITS

 badge

0.25

badge

0.23

CI

0.22

.bad

0.22

-badge

0.21

 Badge

0.21

BAD

0.21

_bad

0.21

 shields

0.20

 badges

0.20

Activations Density 0.006%

references to URLs and file paths, particularly related to code repositories

No Comments

No Known Activations