INDEX

Explanations

instances of significant actions, feelings, and characteristics described in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 pornografia

-0.14

avanaugh

-0.14

 Finally

-0.13

eteria

-0.13

ÑĸÐ¹Ñģ

-0.13

 Affero

-0.13

 finally

-0.13

antlr

-0.13

cano

-0.13

ivicrm

-0.13

POSITIVE LOGITS

 finder

0.15

è¼Ķ

0.15

TO

0.15

 textSize

0.15

ie

0.14

ies

0.14

 Î´Î·

0.14

eydi

0.14

ysa

0.14

Sim

0.14

Activations Density 0.031%

instances of significant actions, feelings, and characteristics described in various contexts

No Comments

No Known Activations