INDEX

Explanations

bibliographic references and citation information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

gnore

-0.16

VENTORY

-0.15

orde

-0.15

 ÐļÑĢÑĸÐ¼

-0.14

iliation

-0.14

olatile

-0.14

à¥įà¤ªà¤°

-0.14

astery

-0.14

irt

-0.13

rieve

-0.13

POSITIVE LOGITS

pp

0.23

 pages

0.17

uns

0.16

ibble

0.16

asic

0.15

 forfe

0.15

ä¸¸

0.14

pp

0.14

Pages

0.14

 Dennis

0.14

Activations Density 0.120%

bibliographic references and citation information

No Comments

No Known Activations