INDEX

Explanations

instances of uncertainty or indecision in various contexts

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

ymb

-0.16

ubat

-0.15

ushima

-0.14

Ø±ÙĪÙģ

-0.14

Ð¾Ð¿Ð°Ñģ

-0.14

logg

-0.14

 èĩªåĬ¨çĶŁæĪĲ

-0.13

plusplus

-0.13

Ð¾Ð´ÐµÑĢÐ¶

-0.13

isis

-0.13

POSITIVE LOGITS

apiro

0.17

lie

0.15

:UITableView

0.15

agh

0.15

 Tome

0.14

dam

0.14

numer

0.14

Ð¶ÐµÐ½ÑĮ

0.14

HEY

0.14

æĺŃ

0.13

Activations Density 0.003%

instances of uncertainty or indecision in various contexts

No Comments

No Known Activations