INDEX

Explanations

phrases related to legal principles and obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.16

olla

-0.14

inks

-0.14

ossier

-0.13

ignment

-0.13

kami

-0.13

 Transparency

-0.13

attering

-0.13

à¸³

-0.13

ereum

-0.13

POSITIVE LOGITS

ADOS

0.19

 Tradition

0.19

Trad

0.18

 traditionally

0.18

 tradition

0.17

 trad

0.17

trad

0.16

vla

0.16

mlink

0.16

cot

0.15

Activations Density 0.952%

phrases related to legal principles and obligations

No Comments

No Known Activations