INDEX

Explanations

references to tags or categories 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

istrovstvÃŃ

-0.17

iscard

-0.16

 Mandal

-0.15

nal

-0.15

APA

-0.15

zb

-0.15

ï»¿↵↵

-0.15

 mastur

-0.14

edback

-0.14

âĢ¢↵↵

-0.14

POSITIVE LOGITS

eli

0.16

åĻ

0.15

ags

0.15

 satire

0.15

vir

0.14

Viv

0.14

 Kons

0.14

agan

0.14

im

0.14

Activations Density 0.010%

references to tags or categories related to content organization

No Comments

No Known Activations