INDEX

Explanations

key terms related to medical professionals and healthcare contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

urd

-0.17

atz

-0.15

thes

-0.15

isco

-0.15

ãĥ³ãĤº

-0.14

Leo

-0.14

 inflation

-0.14

 scen

-0.14

afe

-0.14

craft

-0.14

POSITIVE LOGITS

YLON

0.18

acas

0.15

alian

0.15

ylon

0.15

ÅĻen

0.15

 Schiff

0.15

 cubes

0.14

lij

0.14

ableOpacity

0.14

iddy

0.14

Activations Density 0.109%

key terms related to medical professionals and healthcare contexts

No Comments

No Known Activations