INDEX

Explanations

phrases reflecting conflict and disagreement among individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

amd

-0.15

lech

-0.15

zej

-0.15

 Blank

-0.14

croft

-0.14

gli

-0.14

/post

-0.14

maal

-0.14

ogui

-0.14

ÏģÎ¹Î½

-0.14

POSITIVE LOGITS

 gemeins

0.21

åħ±åĲĮ

0.20

 shared

0.19

 mutual

0.19

åħ±

0.17

 åħ±

0.17

 joint

0.16

.Shared

0.16

common

0.16

 common

0.16

Activations Density 0.398%

phrases reflecting conflict and disagreement among individuals or groups

No Comments

No Known Activations