INDEX

Explanations

terms associated with obtaining or acquiring something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

quarters

-0.19

ened

-0.19

Ã¡k

-0.15

fold

-0.15

-quarters

-0.15

izar

-0.15

thy

-0.14

ening

-0.14

quel

-0.14

POSITIVE LOGITS

rid

0.18

ivant

0.17

vatel

0.17

metatable

0.16

JKLM

0.16

OMEM

0.15

OrElse

0.15

.UnitTesting

0.15

vais

0.14

orsi

0.14

Activations Density 0.034%

terms associated with obtaining or acquiring something

No Comments

No Known Activations