INDEX

Explanations

mentions of 'DC' and its variations, indicating a focus on geographical or organizational references related to 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 @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

agrant

-0.15

 voks

-0.15

an

-0.15

 Burnett

-0.15

ë§¹

-0.15

her

-0.14

 Rupert

-0.14

ÏĨÏħ

-0.14

IALIZ

-0.14

onom

-0.14

POSITIVE LOGITS

DC

0.25

 Comics

0.23

/dc

0.21

dc

0.21

.dc

0.18

DC

0.18

(dc

0.18

oup

0.17

dc

0.17

 portion

0.16

Activations Density 0.015%

mentions of 'DC' and its variations, indicating a focus on geographical or organizational references related to Washington, D.C

No Comments

No Known Activations