INDEX

Explanations

instances of the word "in" associated with locations or contexts

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

ufs

-0.18

ivre

-0.15

.DefaultCellStyle

-0.15

ImageContext

-0.14

ÄĲT

-0.14

 Ø§ÙĦØ¹Ø±Ø¨

-0.14

 runnable

-0.14

">//

-0.14

roll

-0.14

Ð°ÑĢÑĩ

-0.13

POSITIVE LOGITS

.ws

0.16

ÏģÎŃ

0.15

iesel

0.15

fel

0.14

mor

0.14

 flex

0.14

undler

0.14

 Kund

0.14

logg

0.13

 Flex

0.13

Activations Density 0.012%

instances of the word "in" associated with locations or contexts

No Comments

No Known Activations