INDEX

Explanations

questions and inquiries related to programming and technical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ESA

-0.16

 teng

-0.15

efs

-0.14

ahr

-0.14

ÑĥÐºÐ¾Ð²

-0.14

æĢĿãģĦ

-0.14

lbrakk

-0.14

IFI

-0.13

 ìĹ°ëĿ½

-0.13

Uh

-0.13

POSITIVE LOGITS

 stack

0.19

 Stack

0.18

 thanks

0.17

Apr

0.17

 thanked

0.17

è°¢

0.16

 thank

0.16

ercul

0.15

thanks

0.15

Activations Density 0.086%

questions and inquiries related to programming and technical topics

No Comments

No Known Activations