INDEX

Explanations

references to health experts 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 @ 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

.metamodel

-0.16

ØŃÛĮ

-0.15

urette

-0.15

 Blasio

-0.15

inery

-0.14

 kÃ¼t

-0.14

ahlen

-0.14

arus

-0.14

é§Ĩ

-0.14

edic

-0.13

POSITIVE LOGITS

 Fauc

0.18

 Pron

0.17

pul

0.16

ebra

0.16

 Deep

0.16

 infectious

0.16

Fa

0.16

.bs

0.15

 rear

0.15

 Rear

0.15

Activations Density 0.018%

references to health experts and their statements

No Comments

No Known Activations