INDEX

Explanations

features related to accessibility and ease of use in products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

æĬľ

-0.16

-0.15

holm

-0.14

acen

-0.14

loe

-0.14

licit

-0.14

vig

-0.14

ë¨

-0.14

asti

-0.14

lices

-0.14

POSITIVE LOGITS

 Parade

0.15

 habit

0.15

 Habit

0.15

orWhere

0.14

ILES

0.14

ìĿį

0.13

 Duch

0.13

 PROGMEM

0.12

pym

0.12

 ********************************************************************************

0.12

Activations Density 0.167%

features related to accessibility and ease of use in products

No Comments

No Known Activations