INDEX

Explanations

instances of medication and health-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ixe

-0.17

Ì

-0.17

wald

-0.15

ought

-0.15

éŀ

-0.15

otine

-0.14

rought

-0.14

omap

-0.14

 Perception

-0.14

POSITIVE LOGITS

ypy

0.15

ddf

0.14

coni

0.14

HAL

0.14

indr

0.13

ivar

0.13

eut

0.13

adb

0.13

abbo

0.13

macen

0.13

Activations Density 0.358%

instances of medication and health-related terms

No Comments

No Known Activations