INDEX

Explanations

terms related to specific medical conditions and symptoms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

undry

-0.18

aise

-0.17

ester

-0.15

 Myers

-0.15

ikon

-0.15

Î¼Î±Î¹

-0.14

Ã¡r

-0.14

ingen

-0.14

esters

-0.14

wie

-0.13

POSITIVE LOGITS

ãģĵãģ¡ãĤī

0.19

ECTOR

0.18

ector

0.17

é¡¾

0.17

 usually

0.16

 subtype

0.16

 generally

0.15

apt

0.15

istinguished

0.14

 çĶŁåĳ½åĳ¨æľŁåĩ½æķ°

0.14

Activations Density 0.229%

terms related to specific medical conditions and symptoms

No Comments

No Known Activations