INDEX

Explanations

punctuation marks and commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

cob

-0.16

 ç¿

-0.15

usercontent

-0.14

TOOLS

-0.14

ysa

-0.14

isz

-0.14

roker

-0.14

cle

-0.13

eds

-0.13

pear

-0.13

POSITIVE LOGITS

anos

0.15

imeType

0.15

Î»Î¹Î¿

0.15

YLES

0.14

ERRU

0.14

liga

0.14

RIES

0.14

aben

0.14

ushima

0.13

ä½³

0.13

Activations Density 0.010%

punctuation marks and commas

No Comments

No Known Activations