INDEX

Explanations

elements related to scientific publishing and documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

izard

-0.15

inn

-0.14

kins

-0.14

çķ

-0.14

 bone

-0.13

deg

-0.13

 direction

-0.13

ohan

-0.13

 liver

-0.13

 drop

-0.13

POSITIVE LOGITS

 ÑģÐ¸

0.15

ï¼¬

0.14

_rb

0.14

ajas

0.14

 taxa

0.14

ObjectContext

0.14

oty

0.13

 Pháº¡m

0.13

ocha

0.13

-sp

0.13

Activations Density 0.009%

elements related to scientific publishing and documentation

No Comments

No Known Activations