INDEX

Explanations

sections of text related to academic articles or research papers

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

eren

-0.14

sons

-0.14

 Grim

-0.14

erry

-0.14

sek

-0.14

mot

-0.14

 Wind

-0.14

ron

-0.13

ubi

-0.13

Ron

-0.13

POSITIVE LOGITS

riz

0.17

kÃ¡

0.15

aro

0.15

sik

0.15

haar

0.15

velope

0.15

edor

0.14

abis

0.14

¼

0.14

 polls

0.14

Activations Density 0.002%

sections of text related to academic articles or research papers

No Comments

No Known Activations