INDEX

Explanations

geographical locations and names related to specific regions or districts

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

yun

-0.18

ae

-0.17

 exact

-0.15

 Tong

-0.15

asic

-0.14

Bj

-0.14

 subject

-0.14

 pointers

-0.14

 Crow

-0.14

Crow

-0.14

POSITIVE LOGITS

anca

0.18

_compat

0.16

xito

0.15

izo

0.14

bower

0.14

ÑĨÑĸ

0.14

jective

0.14

/*č↵

0.14

robe

0.14

bum

0.13

Activations Density 0.226%

geographical locations and names related to specific regions or districts

No Comments

No Known Activations