INDEX

Explanations

phrases involving the concept of "whole" 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 @ 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

 Lumpur

-0.15

åĭĻ

-0.14

.LayoutStyle

-0.14

elia

-0.14

 certain

-0.13

dit

-0.13

 Lafayette

-0.13

à¸ī

-0.13

åĬ¡

-0.13

its

-0.13

POSITIVE LOGITS

 entire

0.19

æķ´ä¸ª

0.19

process

0.16

 process

0.15

iesen

0.15

 ÙħØ¯Øª

0.14

aybe

0.14

extent

0.14

è¿ĩç¨ĭ

0.14

 whole

0.14

Activations Density 0.040%

phrases involving the concept of "whole" in various contexts

No Comments

No Known Activations