INDEX

Explanations

contrasting phrases or opinions

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

ocol

-0.16

ewis

-0.15

kaar

-0.15

.inline

-0.15

lexport

-0.14

Î¼ÎµÎ½

-0.14

strup

-0.14

rott

-0.14

genden

-0.14

audi

-0.13

POSITIVE LOGITS

enton

0.16

rin

0.14

rone

0.14

Ŀ

0.14

ruh

0.14

archy

0.14

bab

0.13

ler

0.13

 Coupe

0.13

bro

0.13

Activations Density 0.076%

contrasting phrases or opinions

No Comments

No Known Activations