INDEX

Explanations

HTML tags and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

jos

-0.18

vod

-0.17

uum

-0.14

oÅ¡

-0.14

opens

-0.14

awl

-0.14

eum

-0.14

uctor

-0.14

 seeming

-0.14

raid

-0.14

POSITIVE LOGITS

á»ĵm

0.16

abl

0.15

anca

0.14

lemen

0.14

setId

0.14

ì¦Ī

0.14

reta

0.14

ÑĤÐ¸ÑĢÐ¾Ð²

0.14

PERT

0.13

ëĤľ

0.13

Activations Density 0.002%

HTML tags and attributes

No Comments

No Known Activations