INDEX

Explanations

references to manuscripts and their authorship in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ONS

-0.15

loadModel

-0.14

ForResult

-0.14

Äĥm

-0.13

 cere

-0.13

Dot

-0.13

 immortal

-0.13

av

-0.13

 hung

-0.13

èĴ

-0.13

POSITIVE LOGITS

omik

0.16

folios

0.15

/cop

0.15

addle

0.15

anh

0.15

iale

0.15

 å½±

0.14

uÄį

0.14

initialized

0.14

endon

0.14

Activations Density 0.032%

references to manuscripts and their authorship in historical contexts

No Comments

No Known Activations