INDEX

Explanations

terms related to accessibility and inclusivity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

-0.18

 back

-0.17

uze

-0.17

-0.16

fty

-0.15

os

-0.15

ÄĽ

-0.15

 Dirk

-0.15

POSITIVE LOGITS

AMERA

0.21

ibly

0.19

ëĭ¤ê°Ģ

0.16

bstract

0.16

UTO

0.15

-pocket

0.15

å®Ļ

0.15

_vlog

0.15

LARI

0.15

rieg

0.15

Activations Density 0.009%

terms related to accessibility and inclusivity

No Comments

No Known Activations