INDEX

Explanations

medical conditions and terms related to health disorders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

oord

-0.17

Ð¼Ð°Ð·

-0.16

ByExample

-0.15

uÅŁ

-0.15

ozor

-0.14

ë¡±

-0.14

yyy

-0.14

 Mines

-0.14

ursal

-0.14

Ð»Ð°Ð¶

-0.14

POSITIVE LOGITS

ittel

0.15

anki

0.15

nal

0.14

ãĥ¼ãĥī

0.13

ÄĽr

0.13

çģ¯

0.13

Äĵ

0.13

ÑĬ

0.13

lica

0.13

Ú¯Ø§ÙĨ

0.13

Activations Density 0.042%

medical conditions and terms related to health disorders

No Comments

No Known Activations