INDEX

Explanations

mentions of the term "public" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ogle

-0.16

usat

-0.16

zee

-0.16

ross

-0.15

zac

-0.15

STALL

-0.15

opi

-0.14

ood

-0.14

ulings

-0.14

ulle

-0.14

POSITIVE LOGITS

vie

0.18

ayi

0.15

 Sunder

0.15

Ð²Ð¸Ñĩ

0.14

eyed

0.14

 defe

0.14

orno

0.14

ÙĬÙĥÙĬ

0.13

 entity

0.13

 Lands

0.13

Activations Density 0.033%

mentions of the term "public" in various contexts

No Comments

No Known Activations