INDEX

Explanations

terms relating to historical proposals or suggestions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

à¸µà¸¢à¸Ļ

-0.15

 ë°°

-0.15

 rÃºt

-0.15

isoft

-0.15

 queryInterface

-0.14

avis

-0.14

ÐµÑĢÐ±

-0.14

_ONCE

-0.14

dna

-0.14

gesch

-0.14

POSITIVE LOGITS

ipa

0.18

 Trial

0.16

ichen

0.16

IPA

0.15

 Guides

0.15

Tol

0.15

uk

0.15

quent

0.15

IR

0.14

Activations Density 0.000%

terms relating to historical proposals or suggestions

No Comments

No Known Activations