INDEX

Explanations

variations of the word "benefit" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

åľ¨çº¿è§Ĥçľĭ

-0.16

ional

-0.15

ta

-0.14

abra

-0.14

ORIES

-0.14

ophy

-0.14

ney

-0.14

 ÑĤÑıÐ¶

-0.14

autorelease

-0.14

POSITIVE LOGITS

volent

0.24

utzer

0.20

iciary

0.18

 rede

0.18

jamin

0.17

 bene

0.17

velope

0.17

icia

0.17

amat

0.16

fits

0.16

Activations Density 0.016%

variations of the word "benefit" and its related forms

No Comments

No Known Activations