INDEX

Explanations

references to different organizations or departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

elsea

-0.14

 tamp

-0.14

echa

-0.14

ledge

-0.14

 Gang

-0.14

agrid

-0.14

leen

-0.14

resher

-0.14

actory

-0.13

rama

-0.13

POSITIVE LOGITS

 fond

0.18

TableName

0.14

rott

0.14

.crm

0.14

 ç´

0.14

aves

0.13

 åĿ

0.13

¶Į

0.13

Jak

0.13

voj

0.13

Activations Density 0.071%

references to different organizations or departments

No Comments

No Known Activations