INDEX

Explanations

terminology related to medical 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 @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

-0.15

logue

-0.14

viso

-0.14

Ī¬

-0.14

zione

-0.14

-0.13

yntax

-0.13

à¤¬à¤°

-0.13

 Lonely

-0.13

 courtesy

-0.13

POSITIVE LOGITS

Ã¦

0.19

 Wass

0.17

 Koch

0.15

 evils

0.14

 Carrie

0.14

çĤ®

0.14

ritis

0.14

æ¯«

0.14

eton

0.14

 phim

0.14

Activations Density 0.165%

terminology related to medical conditions and treatments

No Comments

No Known Activations