INDEX

Explanations

references to remnants or remnants of the past

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

PM

-0.15

xia

-0.15

licer

-0.15

asin

-0.14

lassian

-0.14

knife

-0.14

IBUT

-0.14

pr

-0.14

ogh

-0.14

nea

-0.14

POSITIVE LOGITS

rem

0.30

Rem

0.27

/rem

0.24

rem

0.23

Rem

0.22

REM

0.22

.rem

0.21

.Rem

0.20

embrance

0.19

ington

0.19

Activations Density 0.016%

references to remnants or remnants of the past

No Comments

No Known Activations