INDEX

Explanations

references to proportions or parts of a whole

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

ailer

-0.16

Ã©

-0.15

itis

-0.15

Ð¾ÑĢÐ¾Ð½

-0.14

kill

-0.14

our

-0.14

orial

-0.14

ajas

-0.14

antal

-0.14

sic

-0.14

POSITIVE LOGITS

course

0.21

-course

0.21

 course

0.18

.scalablytyped

0.17

 sorts

0.17

vester

0.16

alous

0.16

ICI

0.16

iani

0.16

/to

0.15

Activations Density 0.863%

references to proportions or parts of a whole

No Comments

No Known Activations