INDEX

Explanations

references to individuals in photographs and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oka

-0.15

ibar

-0.14

igu

-0.14

å¯Ħ

-0.14

åľ

-0.14

avier

-0.14

pend

-0.14

-0.13

.setOutput

-0.13

Ã¼rn

-0.13

POSITIVE LOGITS

 doing

0.23

perform

0.20

 asleep

0.20

 performing

0.18

 enjoying

0.18

 interacting

0.17

 playing

0.17

 interact

0.16

 inspect

0.16

 making

0.16

Activations Density 0.172%

references to individuals in photographs and their relationships

No Comments

No Known Activations