INDEX

Explanations

references to statistical percentages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ancock

-0.15

otechn

-0.14

uzu

-0.14

yun

-0.14

cci

-0.13

 Jens

-0.13

aris

-0.13

ÑģÐºÐ»Ð°Ð´

-0.13

MBOL

-0.13

andal

-0.13

POSITIVE LOGITS

iles

0.18

lesia

0.17

ofday

0.17

igg

0.15

turnstile

0.14

ayment

0.14

erequisite

0.14

onec

0.14

 Wade

0.14

era

0.14

Activations Density 0.010%

references to statistical percentages

No Comments

No Known Activations