INDEX

Explanations

references to group activities or communal settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

á»ĩ

-0.17

LOPT

-0.17

Ī¬

-0.16

infeld

-0.15

AndView

-0.15

ulp

-0.14

ICLE

-0.14

ibel

-0.14

emez

-0.14

/***/

-0.14

POSITIVE LOGITS

br

0.17

 doGet

0.17

ahlen

0.16

IAS

0.16

 Andrews

0.15

ewan

0.14

pillar

0.14

rieve

0.14

andan

0.14

Activations Density 0.023%

references to group activities or communal settings

No Comments

No Known Activations