INDEX

Explanations

references to documentation or disclaimers related to content organization

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

_CHANGED

-0.14

aldo

-0.14

æľ¬å½ĵ

-0.14

nts

-0.14

ãģĵãĤį

-0.14

WRAPPER

-0.13

XP

-0.13

 Ð¿ÑĢÐ¾Ð³ÑĢÐ°Ð¼

-0.13

(.)

-0.13

POSITIVE LOGITS

.twitch

0.18

 ourselves

0.16

spam

0.15

 spam

0.15

 submitted

0.14

 actively

0.14

mani

0.14

anine

0.14

 submissions

0.14

 manually

0.14

Activations Density 0.003%

references to documentation or disclaimers related to content organization

No Comments

No Known Activations