INDEX

Explanations

specialized terms and phrases related to scientific or technical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Nem

-0.15

arena

-0.14

ire

-0.14

LAN

-0.14

IMO

-0.14

çĬ¶

-0.14

sut

-0.14

RARY

-0.13

 ilan

-0.13

ownik

-0.13

POSITIVE LOGITS

ins

0.52

ÃŃn

0.50

Ð¸Ð½

0.46

IN

0.45

in

0.44

ÛĮÙĨ

0.41

ãĤ¤ãĥ³

0.41

ÑĸÐ½

0.40

INS

0.40

à¤¿à¤¨

0.38

Activations Density 0.168%

specialized terms and phrases related to scientific or technical concepts

No Comments

No Known Activations