INDEX

Explanations

references to specific locations and events in Washington, D.C

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

presso

-0.18

 national

-0.15

ãĥ³ãĥķ

-0.15

 Hayward

-0.15

-pres

-0.15

spath

-0.15

 Ethnic

-0.15

 Wash

-0.14

(NS

-0.14

Î±Î¹Î½

-0.14

POSITIVE LOGITS

 Mayor

0.20

Mayor

0.20

Omn

0.18

ANC

0.16

Council

0.16

 mayor

0.15

 Council

0.15

§è¡Į

0.15

 Gray

0.15

icity

0.14

Activations Density 0.006%

references to specific locations and events in Washington, D.C

No Comments

No Known Activations