INDEX

Explanations

elevated terms associated with health or medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.15

-0.14

 commissioned

-0.14

opsis

-0.14

 grunt

-0.14

olin

-0.13

 sorte

-0.13

longitude

-0.13

POSITIVE LOGITS

wnd

0.17

ypi

0.15

Ã±a

0.14

ickey

0.14

Py

0.14

erville

0.14

ÑĢÐ¾Ð´

0.14

âĹİ

0.13

 intro

0.13

.doc

0.13

Activations Density 0.011%

elevated terms associated with health or medical conditions

No Comments

No Known Activations