INDEX

Explanations

phrases that express an increase or amplification of a quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

chn

-0.15

quir

-0.15

åĲįçĦ¡ãģĹ

-0.14

seau

-0.14

.cfg

-0.14

ç©¶

-0.14

idual

-0.14

chen

-0.14

_Arg

-0.14

POSITIVE LOGITS

oley

0.16

ude

0.15

emens

0.14

swick

0.14

uzey

0.14

umnos

0.14

 republik

0.14

endet

0.14

ouden

0.14

ecture

0.14

Activations Density 0.035%

phrases that express an increase or amplification of a quality

No Comments

No Known Activations