INDEX

Explanations

URLs and web-related terms

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

mlin

-0.18

PLEX

-0.14

dro

-0.14

ungal

-0.14

atron

-0.14

 NSStringFromClass

-0.14

rant

-0.14

mploy

-0.13

cies

-0.13

orce

-0.13

POSITIVE LOGITS

.bn

0.15

))[

0.15

raki

0.14

apas

0.14

 rest

0.13

 Maur

0.13

odom

0.13

íĦ°

0.13

 ngOn

0.13

Activations Density 0.001%

URLs and web-related terms

No Comments

No Known Activations