INDEX

Explanations

contexts involving abundance or a variety of options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

and

-0.15

cker

-0.14

JI

-0.14

afort

-0.14

_RW

-0.13

asa

-0.13

\Schema

-0.13

 Huff

-0.12

uzu

-0.12

ji

-0.12

POSITIVE LOGITS

 besides

0.27

 importantly

0.23

ebek

0.17

eter

0.16

 Besides

0.16

misc

0.15

others

0.15

ëłĩ

0.14

orraine

0.14

Besides

0.14

Activations Density 0.041%

contexts involving abundance or a variety of options

No Comments

No Known Activations