INDEX

Explanations

URLs and links to resources

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

etat

-0.19

@(

-0.17

eyJ

-0.15

ÑĢÐ¾Ð´

-0.15

.gov

-0.15

ycin

-0.15

izons

-0.14

amura

-0.14

panied

-0.14

.gateway

-0.14

POSITIVE LOGITS

github

0.24

code

0.23

stackoverflow

0.21

programming

0.19

 Code

0.18

Code

0.18

Programming

0.18

.github

0.17

 github

0.17

software

0.17

Activations Density 0.033%

URLs and links to resources

No Comments

No Known Activations