INDEX

Explanations

terms related to scientific categorization and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ÐµÐ»Ð¾Ð²

-0.16

kte

-0.15

ple

-0.14

à¤¾à¤ĩà¤²

-0.14

bbie

-0.14

 Emit

-0.14

implify

-0.14

ervoir

-0.14

ully

-0.13

ahir

-0.13

POSITIVE LOGITS

ica

0.38

ico

0.35

icos

0.35

ICA

0.29

icamente

0.28

icas

0.27

icus

0.25

ICO

0.24

iques

0.23

icode

0.21

Activations Density 0.033%

terms related to scientific categorization and representation

No Comments

No Known Activations