INDEX

Explanations

details related to legal cases, court opinions, and their citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

 nomin

-0.16

 continuity

-0.15

 vera

-0.14

edis

-0.14

olland

-0.14

urtles

-0.14

omor

-0.14

plist

-0.14

apos

-0.14

 stap

-0.14

POSITIVE LOGITS

 addCriterion

0.17

inese

0.14

à¸´à¸Ļà¸Ĺà¸£

0.14

Poz

0.14

azon

0.14

-du

0.13

mgr

0.13

å±ħæ°ĳ

0.13

ay

0.13

Activations Density 0.004%

details related to legal cases, court opinions, and their citations

No Comments

No Known Activations