INDEX

Explanations

URLs and file formats related to images or documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 Shel

-0.16

odel

-0.15

instein

-0.15

à¸ģà¸£à¸¡

-0.14

amespace

-0.14

achuset

-0.14

ucch

-0.14

orado

-0.14

igen

-0.14

ltra

-0.14

POSITIVE LOGITS

://

0.27

wire

0.16

 Marl

0.14

Ŀ

0.14

 Franken

0.14

ë¡Ŀ

0.13

_simps

0.13

ARY

0.13

nic

0.13

ALTH

0.13

Activations Density 0.003%

URLs and file formats related to images or documentation

No Comments

No Known Activations