INDEX

Explanations

various stages and performance metrics in a racing context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 repmat

-0.15

.PropTypes

-0.14

upported

-0.14

orra

-0.14

LEEP

-0.14

Van

-0.14

UPPORTED

-0.13

 weaken

-0.13

cup

-0.13

.history

-0.13

POSITIVE LOGITS

MZ

0.13

indre

0.13

TON

0.13

assium

0.13

yer

0.13

Keeper

0.13

 CONSEQUENTIAL

0.12

à¸²à¸°

0.12

qli

0.12

ogi

0.12

Activations Density 0.041%

various stages and performance metrics in a racing context

No Comments

No Known Activations