INDEX

Explanations

elements related to user interface interactions and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ancode

-0.16

tas

-0.15

 Kash

-0.15

landÄ±r

-0.15

olley

-0.14

quoi

-0.14

ivol

-0.14

Bind

-0.14

ystick

-0.14

.CustomButton

-0.14

POSITIVE LOGITS

.TRUE

0.18

TRUE

0.17

ColumnsMode

0.15

SED

0.15

 ÙħØ³Ø¦ÙĪÙĦ

0.15

=YES

0.15

 FALSE

0.15

 TRUE

0.14

FALSE

0.14

aye

0.14

Activations Density 0.067%

elements related to user interface interactions and preferences

No Comments

No Known Activations