INDEX

Explanations

legal and judicial terms or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

errat

-0.16

colo

-0.16

 voks

-0.16

 samot

-0.15

orners

-0.15

ude

-0.14

Î¹Î¬

-0.14

kli

-0.14

Ãºi

-0.14

undy

-0.14

POSITIVE LOGITS

Ł

0.16

uste

0.15

iscal

0.14

 parad

0.13

 basket

0.13

ustr

0.13

 Ð§Ð¸

0.13

agen

0.13

 postponed

0.13

 OMIT

0.13

Activations Density 0.012%

legal and judicial terms or references

No Comments

No Known Activations