INDEX

Explanations

variations of the word "mimic" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

elly

-0.17

xon

-0.16

.toObject

-0.15

bilt

-0.15

storybook

-0.15

annah

-0.15

ellas

-0.14

 Cousins

-0.14

Ã¡h

-0.14

Ð°ÑĢÐ¾Ð´

-0.14

POSITIVE LOGITS

icking

0.27

icked

0.23

ics

0.22

etic

0.20

iliki

0.19

osa

0.18

imi

0.18

URA

0.18

.deepcopy

0.17

nesota

0.17

Activations Density 0.007%

variations of the word "mimic" and related terms

No Comments

No Known Activations