INDEX

Explanations

references to digital content and online interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 SUBJECT

-0.14

ersion

-0.14

Ã¦r

-0.14

.vertx

-0.14

ersions

-0.14

 Patterson

-0.14

Ð·Ð°Ð±

-0.14

èı

-0.13

="#">

-0.13

 subject

-0.13

POSITIVE LOGITS

oker

0.16

 Sharma

0.15

0.14

 Shar

0.14

olson

0.14

lamaz

0.14

Ã´me

0.14

å¡ĳ

0.13

Activations Density 0.002%

references to digital content and online interactions

No Comments

No Known Activations