INDEX

Explanations

scientific classifications or taxonomic details related to species

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

via

-0.18

oret

-0.16

onga

-0.15

ttp

-0.15

Via

-0.15

ltra

-0.14

 Lack

-0.14

urga

-0.14

afen

-0.14

assage

-0.14

POSITIVE LOGITS

atak

0.16

IOC

0.15

obl

0.14

XF

0.14

ums

0.14

 Watches

0.13

Zuk

0.13

 pledged

0.13

_BR

0.13

_hpp

0.13

Activations Density 0.007%

scientific classifications or taxonomic details related to species

No Comments

No Known Activations