INDEX

Explanations

numerical data in various formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ÑĢÑıÐ´

-0.16

kav

-0.15

RuleContext

-0.15

stan

-0.15

etal

-0.15

Kra

-0.15

compact

-0.14

enties

-0.14

æ¯Ľ

-0.13

åĢŁ

-0.13

POSITIVE LOGITS

0.33

0.29

0.28

0.27

Activations Density 0.131%

numerical data in various formats

No Comments

No Known Activations