INDEX

Explanations

medical terminology related to conditions and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

zcze

-0.17

NGX

-0.16

Ø¨ÙĪØ§Ø³Ø·Ø©

-0.15

ãĤ¤ãĤº

-0.14

ì§ĢëıĦ

-0.14

ertia

-0.14

orial

-0.14

roke

-0.14

rÃ¥

-0.14

ç¾½

-0.14

POSITIVE LOGITS

ky

0.27

 curve

0.23

 curves

0.23

 curvature

0.22

 deform

0.22

Ky

0.22

 bowed

0.21

-cur

0.21

Curve

0.21

 corrective

0.20

Activations Density 0.009%

medical terminology related to conditions and treatments

No Comments

No Known Activations