INDEX

Explanations

references to geographical locations and administrative divisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

/topic

-0.16

 Mast

-0.16

cie

-0.16

istory

-0.16

.bz

-0.15

imli

-0.15

èķī

-0.14

iske

-0.14

 jadx

-0.14

grese

-0.14

POSITIVE LOGITS

 press

0.15

bla

0.14

 Press

0.14

à¹Ħ

0.13

ation

0.13

-mar

0.13

Ø§ØªÛĮ

0.13

elig

0.13

ency

0.13

Activations Density 0.003%

references to geographical locations and administrative divisions

No Comments

No Known Activations