INDEX

Explanations

judicial references and legal terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 DISCLAIM

-0.17

.heroku

-0.17

imits

-0.16

pap

-0.15

 Hast

-0.14

ãĥ¼ãĥĸãĥ«

-0.14

 powdered

-0.14

ella

-0.14

ëłĪìĿ´

-0.14

Mahon

-0.13

POSITIVE LOGITS

 Branch

0.19

 chan

0.19

branch

0.19

 prayed

0.17

Branch

0.17

chan

0.17

 afore

0.16

RTC

0.16

.pet

0.16

RTC

0.15

Activations Density 0.005%

judicial references and legal terminology

No Comments

No Known Activations