INDEX

Explanations

references to medical professionals and their roles

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

áº¡ng

-0.17

kÃ¡

-0.15

geber

-0.15

tas

-0.15

ties

-0.15

ÏĩÏĮ

-0.15

ti

-0.14

illy

-0.14

ancer

-0.14

atak

-0.14

POSITIVE LOGITS

ate

0.25

ial

0.24

/engine

0.21

 treating

0.21

 prescribing

0.20

/ph

0.20

 assistant

0.18

 assistants

0.17

/providers

0.17

 offices

0.16

Activations Density 0.058%

references to medical professionals and their roles

No Comments

No Known Activations