INDEX

Explanations

mentions of health-related topics and locations associated with medical discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

cot

-0.16

czy

-0.15

heimer

-0.15

rens

-0.15

illo

-0.14

quine

-0.14

erras

-0.14

 seeded

-0.14

lesi

-0.14

zell

-0.14

POSITIVE LOGITS

iri

0.14

loub

0.14

ê´ĳ

0.14

ç´

0.14

_PULL

0.13

GIT

0.13

 Sullivan

0.13

GetObject

0.13

elli

0.13

GY

0.13

Activations Density 0.009%

mentions of health-related topics and locations associated with medical discussions

No Comments

No Known Activations