INDEX

Explanations

terms related to medical or scientific contexts, particularly focusing on medications and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

marks

-0.18

sti

-0.16

ighton

-0.16

Orm

-0.16

elling

-0.15

íĮĲ

-0.15

spiel

-0.15

-0.14

agens

-0.14

ise

-0.14

POSITIVE LOGITS

sembl

0.19

-Pacific

0.16

paragus

0.16

LIK

0.16

/as

0.16

ylland

0.16

omatic

0.15

<?,

0.15

alborg

0.15

uluk

0.15

Activations Density 0.043%

terms related to medical or scientific contexts, particularly focusing on medications and their effects

No Comments

No Known Activations