INDEX

Explanations

references to population density and demographic data

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

(æ°´

-0.19

SSERT

-0.17

gnore

-0.16

orate

-0.15

CEPTION

-0.15

¼

-0.15

 WCHAR

-0.15

(æľ¨

-0.15

.toolbox

-0.15

hue

-0.14

POSITIVE LOGITS

 Buch

0.16

ahlen

0.15

mat

0.15

 jurisdiction

0.14

Activations Density 0.008%

references to population density and demographic data

No Comments

No Known Activations