INDEX

Explanations

concepts of shared attributes and similarities among various elements or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

egra

-0.17

ernaut

-0.16

acom

-0.16

 neod

-0.15

osit

-0.15

quam

-0.15

reau

-0.14

redient

-0.14

ayload

-0.14

 Unsafe

-0.14

POSITIVE LOGITS

 between

0.16

commons

0.15

vr

0.15

TES

0.14

Ð±Ð¸

0.14

 inverted

0.14

nar

0.14

INGTON

0.14

 across

0.14

igu

0.14

Activations Density 0.240%

concepts of shared attributes and similarities among various elements or systems

No Comments

No Known Activations