INDEX

Explanations

descriptions of intensity and magnitude in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ansa

-0.17

uktur

-0.15

ynn

-0.15

ucha

-0.14

Dix

-0.14

uben

-0.14

amble

-0.14

inh

-0.14

EP

-0.14

afx

-0.14

POSITIVE LOGITS

á»įn

0.18

EAR

0.14

ondo

0.14

ÙĦØª

0.14

asil

0.14

 asteroid

0.13

thood

0.13

-Regular

0.13

.Regular

0.13

OND

0.13

Activations Density 0.246%

descriptions of intensity and magnitude in various contexts

No Comments

No Known Activations

descriptions of intensity and magnitude in various contexts

No Comments

No Known Activations