INDEX

Explanations

references to uniformity and standardization 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

nt

-0.17

ors

-0.17

tin

-0.16

ive

-0.15

rian

-0.15

leigh

-0.15

breaking

-0.14

.CONFIG

-0.14

utenberg

-0.14

 Fuller

-0.14

POSITIVE LOGITS

ities

0.21

ity

0.18

estead

0.17

eting

0.17

ication

0.16

bread

0.16

estar

0.16

è¡¡

0.16

iac

0.16

uito

0.16

Activations Density 0.052%

references to uniformity and standardization in various contexts

No Comments

No Known Activations