INDEX

Explanations

references to medical professionals and their statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ovÃ¡

-0.15

 tuto

-0.15

inas

-0.15

.metamodel

-0.15

teg

-0.14

andles

-0.14

 odst

-0.14

à¸£à¸°

-0.14

antes

-0.14

andas

-0.14

POSITIVE LOGITS

ebra

0.19

 Deep

0.18

.bs

0.17

 comb

0.15

 lead

0.15

Dr

0.15

Uz

0.15

nap

0.14

 Tarif

0.14

ounces

0.14

Activations Density 0.037%

references to medical professionals and their statements

No Comments

No Known Activations