INDEX

Explanations

terms related to healthcare, support services, and treatment conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

Ĵ

-0.16

infeld

-0.15

elps

-0.15

ulado

-0.15

rightness

-0.15

arians

-0.15

ophys

-0.14

mites

-0.14

ises

-0.14

POSITIVE LOGITS

ator

0.68

tor

0.62

ators

0.60

ATOR

0.56

itor

0.54

otor

0.53

Ð°ÑĤÐ¾ÑĢ

0.52

atore

0.51

ador

0.50

TOR

0.48

Activations Density 0.109%

terms related to healthcare, support services, and treatment conditions

No Comments

No Known Activations