INDEX

Explanations

requests for additional information

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

crit

-0.15

iec

-0.14

ITU

-0.14

 Hilton

-0.14

ru

-0.14

nuts

-0.14

orious

-0.13

 ÐĴÐ¸

-0.13

land

-0.13

POSITIVE LOGITS

ãĥ¼ãĥĭ

0.16

ardown

0.16

ntity

0.15

unittest

0.15

aggable

0.15

agina

0.14

Ukr

0.14

 Moist

0.14

xies

0.14

Ľi

0.14

Activations Density 0.013%

requests for additional information

No Comments

No Known Activations