INDEX

Explanations

references to vehicle specifications and performance evaluation

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

 Vapor

-0.16

 vapor

-0.16

 Jame

-0.15

 leveling

-0.15

_gas

-0.15

ethyst

-0.15

 rumored

-0.15

 leveled

-0.15

 neighbor

-0.14

 fiber

-0.14

POSITIVE LOGITS

 boot

0.21

 Boot

0.17

 fraction

0.17

boot

0.17

/boot

0.16

Wol

0.16

ä»

0.16

Boot

0.16

jango

0.16

 alloy

0.16

Activations Density 0.210%

references to vehicle specifications and performance evaluation

No Comments

No Known Activations