INDEX

Explanations

metadata documentation comments in code

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

åĽ£

-0.15

 prefs

-0.14

efe

-0.14

ixel

-0.14

orz

-0.14

_ly

-0.14

_prefs

-0.14

vig

-0.14

library

-0.14

oz

-0.14

POSITIVE LOGITS

atrix

0.16

eing

0.15

icks

0.15

ebi

0.14

 Trom

0.13

AppBundle

0.13

olis

0.13

indsay

0.13

 Bender

0.13

.twig

0.12

Activations Density 0.005%

metadata documentation comments in code

No Known Activations