INDEX

Explanations

parenthetical elements or punctuation marks within the text

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

IEW

-0.15

 over

-0.15

TextWriter

-0.15

utto

-0.14

Ã¼re

-0.14

ordova

-0.13

jist

-0.13

 agreg

-0.13

į°

-0.13

ord

-0.13

POSITIVE LOGITS

ngo

0.15

SYNC

0.15

ecz

0.14

 Sherman

0.14

 erotique

0.14

edef

0.14

estroy

0.14

 ApiController

0.14

bung

0.14

ories

0.13

Activations Density 0.003%

parenthetical elements or punctuation marks within the text

No Comments

No Known Activations