INDEX

Explanations

references to technical issues or error messages in software

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

rios

-0.15

NSNotification

-0.15

hus

-0.14

ONGO

-0.14

å£«

-0.14

ãĥ¼ãĥľ

-0.14

 âĸĪ

-0.13

å¹ħ

-0.13

å¯Ħ

-0.13

|int

-0.13

POSITIVE LOGITS

URL

0.21

rewrite

0.20

www

0.19

URL

0.19

 landing

0.18

.domain

0.18

url

0.18

-www

0.18

 Rewrite

0.17

Activations Density 0.084%

references to technical issues or error messages in software

No Comments

No Known Activations