INDEX

Explanations

instances of listing or cataloging information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

eye

-0.15

letter

-0.14

ihar

-0.14

ÑģÐ°

-0.14

 vá»¥

-0.13

 Wenger

-0.13

steen

-0.13

ye

-0.13

egot

-0.13

ä»¤

-0.13

POSITIVE LOGITS

 datab

0.18

ambi

0.16

inha

0.16

æķ°æį®åºĵ

0.15

Dun

0.15

 database

0.15

portun

0.15

agua

0.15

uptools

0.15

0.14

Activations Density 0.009%

instances of listing or cataloging information

No Comments

No Known Activations