INDEX

Explanations

punctuation marks and their connected expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

strict

-0.16

à¸Ĺà¸£à¸ĩ

-0.15

modifiable

-0.15

ĵĺ

-0.15

ÏĦÎ¯

-0.15

utes

-0.14

 desar

-0.14

entifier

-0.14

POSITIVE LOGITS

0.23

DDD

0.20

roll

0.19

Ds

0.18

rolling

0.17

0.16

(↵

0.16

DD

0.16

PPP

0.16

Activations Density 0.020%

punctuation marks and their connected expressions

No Comments

No Known Activations