INDEX

Explanations

punctuation marks and their patterns in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ARAM

-0.15

avig

-0.13

ç±

-0.13

ØºÙĨ

-0.13

Collision

-0.13

vinces

-0.13

Ã©rie

-0.13

LAG

-0.12

MOVED

-0.12

UNDLE

-0.12

POSITIVE LOGITS

opsis

0.17

Pey

0.14

 dash

0.14

uger

0.14

querque

0.13

ossal

0.13

rog

0.13

resh

0.13

:UI

0.13

oupon

0.13

Activations Density 0.873%

punctuation marks and their patterns in the text

No Comments

No Known Activations