INDEX

Explanations

numerical data and associated statistics

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

ÙİØ¹

-0.15

aram

-0.15

anz

-0.14

 å¯

-0.14

 gross

-0.14

cope

-0.14

anel

-0.14

anka

-0.14

asser

-0.14

udo

-0.14

POSITIVE LOGITS

endor

0.17

Pid

0.15

fen

0.14

arp

0.14

AndView

0.14

_PUSHDATA

0.14

loys

0.14

ViewInit

0.14

»

0.13

elson

0.13

Activations Density 0.042%

numerical data and associated statistics

No Comments

No Known Activations