INDEX

Explanations

questions and inquiries regarding situations or decisions

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

Ø²Ø±

-0.16

 Svens

-0.15

à¹ĥà¸«

-0.15

acers

-0.15

agli

-0.15

 Becker

-0.15

mdir

-0.14

 Oaks

-0.14

wap

-0.14

 subt

-0.14

POSITIVE LOGITS

inal

0.15

 ÙħÙĤØ¯

0.15

<>

0.15

hei

0.15

abella

0.15

kommen

0.14

nearest

0.14

iance

0.14

igg

0.14

oft

0.14

Activations Density 0.098%

questions and inquiries regarding situations or decisions

No Comments

No Known Activations