INDEX

Explanations

negative expressions related to personal dissatisfaction and liability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ija

-0.19

rese

-0.17

 Ä°h

-0.16

unifu

-0.14

ewe

-0.14

velle

-0.14

å¥ĩ

-0.14

-Sah

-0.14

wi

-0.14

 Hast

-0.14

POSITIVE LOGITS

isky

0.15

amina

0.15

 Marcus

0.15

andalone

0.14

ora

0.14

tir

0.14

tera

0.14

ismatch

0.14

ronics

0.14

eworld

0.13

Activations Density 0.272%

negative expressions related to personal dissatisfaction and liability

No Comments

No Known Activations