INDEX

Explanations

nouns and verbs that indicate actions, associations, or key attributes in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ULE

-0.16

apa

-0.15

elm

-0.15

ocy

-0.15

ijke

-0.14

á»ĭp

-0.14

odont

-0.14

GBK

-0.14

USA

-0.14

ailer

-0.14

POSITIVE LOGITS

ABS

0.17

 ragazze

0.16

imoto

0.15

chars

0.15

.cloudflare

0.15

 KromÄĽ

0.15

erness

0.15

aland

0.15

avored

0.14

ä¹ĭä¸Ģ

0.14

Activations Density 0.002%

nouns and verbs that indicate actions, associations, or key attributes in various contexts

No Comments

No Known Activations