INDEX

Explanations

mathematical equations and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rawn

-0.16

ieder

-0.15

uci

-0.15

nio

-0.14

rena

-0.14

ÑĥÑĩÐ°

-0.13

lov

-0.13

imetype

-0.13

 eyed

-0.13

TIM

-0.13

POSITIVE LOGITS

 paran

0.16

 Lambert

0.16

asaki

0.16

 course

0.15

small

0.15

archy

0.15

 small

0.15

udu

0.14

umont

0.14

 Mons

0.14

Activations Density 0.072%

mathematical equations and expressions

No Comments

No Known Activations