INDEX

Explanations

attributes related to configurations or settings within a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

leitung

-0.15

ab

-0.15

atorial

-0.15

ung

-0.15

Ø¯Ø§Ø±ÛĮ

-0.14

ropoda

-0.14

igma

-0.14

ARNING

-0.14

rid

-0.14

igeria

-0.14

POSITIVE LOGITS

.ct

0.15

constitution

0.15

 Woodward

0.14

 constitution

0.14

á»ĳi

0.14

ascript

0.14

/xhtml

0.14

0.13

Activations Density 0.007%

attributes related to configurations or settings within a technical context

No Comments

No Known Activations