INDEX

Explanations

references to organizational roles and positions within a corporate or group structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

jian

-0.17

eras

-0.16

roc

-0.15

itect

-0.15

HASH

-0.15

ĥĿ

-0.14

HIR

-0.14

 Bilim

-0.14

akov

-0.14

 patt

-0.14

POSITIVE LOGITS

ltk

0.17

Fol

0.16

anship

0.15

Ã¦re

0.15

stants

0.15

azi

0.15

vap

0.14

metro

0.14

)prepare

0.14

egis

0.14

Activations Density 0.242%

references to organizational roles and positions within a corporate or group structure

No Comments

No Known Activations