INDEX

Explanations

elements related to emotion and expression

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

CEL

-0.14

adge

-0.14

cko

-0.14

AINS

-0.14

-vers

-0.14

.isNullOrEmpty

-0.14

kbd

-0.13

_SRV

-0.13

_consts

-0.13

ading

-0.13

POSITIVE LOGITS

 otherwise

0.26

otherwise

0.21

 proceedings

0.19

 Otherwise

0.18

 OTHERWISE

0.17

0.15

adores

0.15

se

0.15

auce

0.14

jit

0.14

Activations Density 0.166%

elements related to emotion and expression

No Comments

No Known Activations