INDEX

Explanations

legal terminology related to liability and validity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

urga

-0.17

pery

-0.16

Äįe

-0.16

ola

-0.15

oucher

-0.15

usi

-0.14

 Prep

-0.14

pons

-0.14

owitz

-0.14

æŃ

-0.13

POSITIVE LOGITS

lass

0.16

 vede

0.15

elho

0.15

Î¬Î²

0.15

loff

0.14

 Advocate

0.14

çĤİ

0.14

Ef

0.14

 Ralph

0.14

lish

0.14

Activations Density 0.002%

legal terminology related to liability and validity

No Comments

No Known Activations