INDEX

Explanations

the presence of index-related terms in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ikk

-0.19

ipa

-0.18

aken

-0.17

íģ¼

-0.16

æħĭ

-0.16

ARGIN

-0.15

ampo

-0.15

ä¿Ĺ

-0.15

iche

-0.15

lier

-0.15

POSITIVE LOGITS

-ÑĤÐ¾

0.22

istrovstvÃŃ

0.21

../../../

0.18

à¤¼à¥ĭ

0.17

ing

0.17

plorer

0.17

ional

0.17

yonel

0.16

hai

0.16

eter

0.16

Activations Density 0.053%

the presence of index-related terms in the text

No Comments

No Known Activations