INDEX

Explanations

references to medical or scientific research findings and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 inval

-0.15

ittel

-0.14

 ç§

-0.13

ful

-0.13

gid

-0.13

 consect

-0.13

>Lorem

-0.13

èº

-0.13

itas

-0.13

 Samp

-0.13

POSITIVE LOGITS

uw

0.16

edly

0.15

DOMNode

0.15

aler

0.15

eger

0.15

edback

0.15

OwnProperty

0.14

agi

0.13

 defaultMessage

0.13

 Seal

0.13

Activations Density 0.306%

references to medical or scientific research findings and methodologies

No Comments

No Known Activations