INDEX

Explanations

medical procedures and related contexts

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

ostat

-0.15

razier

-0.15

aginator

-0.15

ibri

-0.14

oÅ¾

-0.14

ouver

-0.14

RESULTS

-0.14

ê¼

-0.14

latlong

-0.14

 dish

-0.13

POSITIVE LOGITS

 anesthesia

0.52

ana

0.47

sed

0.39

Ana

0.39

esthesia

0.37

An

0.34

Ana

0.34

ana

0.32

Sed

0.31

esthetic

0.30

Activations Density 0.079%

medical procedures and related contexts

No Comments

No Known Activations