INDEX

Explanations

terms related to health conditions and medical assessments

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

contri

-0.15

riter

-0.15

esel

-0.14

ylan

-0.14

_domain

-0.13

rite

-0.13

ÚĨ

-0.13

orate

-0.13

ç«

-0.13

ror

-0.13

POSITIVE LOGITS

jem

0.17

razier

0.16

iesel

0.16

ãĥ³ãĥĨãĤ£

0.14

WC

0.14

NotFoundError

0.14

ERE

0.14

underscore

0.13

od

0.13

alg

0.13

Activations Density 0.280%

terms related to health conditions and medical assessments

No Comments

No Known Activations