INDEX

Explanations

special characters or symbols 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

sole

-0.16

ei

-0.15

gaard

-0.14

meer

-0.14

dale

-0.14

\-

-0.13

Ã¥de

-0.13

idelberg

-0.13

antar

-0.13

ALLOC

-0.13

POSITIVE LOGITS

agma

0.16

ç½ļ

0.15

ryo

0.15

ASET

0.14

 Webb

0.14

Cle

0.14

sic

0.14

tainment

0.14

à¸£à¸¡

0.14

^K

0.14

Activations Density 0.002%

special characters or symbols in the text

No Comments

No Known Activations