INDEX

Explanations

structured academic references and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

tal

-0.16

ondo

-0.15

Ã¨res

-0.14

agen

-0.14

uh

-0.14

 exercises

-0.14

Persistence

-0.14

\grid

-0.14

/Sub

-0.14

Wis

-0.13

POSITIVE LOGITS

ÑĤÐµÑĢ

0.15

ucht

0.15

ktor

0.15

ITHER

0.14

à¥įà¤Łà¤°

0.14

boxed

0.14

 Innoc

0.14

Î¼Î¿ÏĤ

0.14

 Arbor

0.14

tera

0.13

Activations Density 0.138%

structured academic references and citations

No Comments

No Known Activations