INDEX

Explanations

concepts related to emotions and interpersonal trust

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

Ã¡cil

-0.15

utc

-0.15

utto

-0.14

 æ±

-0.14

hell

-0.14

erte

-0.14

ipeline

-0.14

æ´¥

-0.14

uto

-0.14

mino

-0.14

POSITIVE LOGITS

 misplaced

0.35

 justified

0.33

 warranted

0.28

 founded

0.22

 deserved

0.22

 justify

0.22

 justification

0.22

-founded

0.21

unf

0.20

arrant

0.19

Activations Density 0.206%

concepts related to emotions and interpersonal trust

No Comments

No Known Activations