INDEX

Explanations

variations of the term 'acceptable'

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

eling

-0.21

pper

-0.16

lom

-0.15

OME

-0.14

uell

-0.14

xy

-0.14

kÃ³w

-0.14

ç¦

-0.14

elled

-0.14

POSITIVE LOGITS

ably

0.20

 Boeh

0.19

hay

0.19

uku

0.15

ately

0.15

ivant

0.15

 Nolan

0.14

folios

0.14

 sufficient

0.14

afen

0.14

Activations Density 0.017%

variations of the term 'acceptable'

No Comments

No Known Activations