INDEX

Explanations

references to community or group-related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

rets

-0.16

 Wich

-0.14

trag

-0.14

imonials

-0.13

asu

-0.13

 carte

-0.13

uto

-0.13

ugu

-0.13

 League

-0.13

arr

-0.13

POSITIVE LOGITS

illac

0.15

uang

0.15

ÅĽnie

0.15

ÑĥÑĢÐ½

0.14

arend

0.14

Å¡em

0.14

 âĸĳ

0.14

Ã¡zal

0.14

 ÙĪØ§Ø±Ø¯

0.14

ØªÙģ

0.14

Activations Density 0.102%

references to community or group-related activities

No Comments

No Known Activations