INDEX

Explanations

references to medical conditions and recovery processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

consts

-0.16

ī

-0.15

inos

-0.15

izont

-0.15

lul

-0.14

izens

-0.14

ullen

-0.14

EEP

-0.13

 Lens

-0.13

 hearts

-0.13

POSITIVE LOGITS

 paralysis

0.35

 paralyzed

0.30

par

0.28

 motor

0.27

 Motor

0.25

motor

0.24

 MOTOR

0.23

Motor

0.22

Par

0.22

 quad

0.21

Activations Density 0.047%

references to medical conditions and recovery processes

No Comments

No Known Activations