INDEX

Explanations

references to online entertainment content

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 combin

-0.14

cher

-0.14

reiben

-0.14

 Olson

-0.14

linger

-0.14

igos

-0.14

UB

-0.14

 Charging

-0.13

ibo

-0.13

POSITIVE LOGITS

OrNil

0.17

niÄį

0.15

Ø³ØªØ§ÙĨ

0.14

 RoundedRectangleBorder

0.14

adin

0.14

ypse

0.14

ÙıÙĨ

0.13

 Giles

0.13

 Morav

0.13

iske

0.13

Activations Density 0.000%

references to online entertainment content

No Comments

No Known Activations