INDEX

Explanations

phrases related to group behavior and dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

tob

-0.17

 poll

-0.16

ura

-0.15

et

-0.15

 chart

-0.15

ined

-0.14

 quot

-0.14

 spor

-0.14

 sensit

-0.13

peater

-0.13

POSITIVE LOGITS

ingroup

0.23

//{{

0.20

 Trait

0.19

 norms

0.17

Trait

0.17

 norm

0.17

Norm

0.17

 schemas

0.17

 Constr

0.17

igroup

0.17

Activations Density 0.124%

phrases related to group behavior and dynamics

No Comments

No Known Activations