INDEX

Explanations

specific terms and phrases related to legal and regulatory contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

lets

-0.15

BOR

-0.15

isz

-0.15

kovi

-0.14

gere

-0.14

Rag

-0.14

 Spirit

-0.14

 Beitrag

-0.14

let

-0.14

bor

-0.14

POSITIVE LOGITS

 Worth

0.19

 worth

0.19

worth

0.17

 indeed

0.16

inde

0.16

wner

0.16

åħĥ

0.16

 merit

0.15

anguage

0.14

oref

0.14

Activations Density 0.007%

specific terms and phrases related to legal and regulatory contexts

No Comments

No Known Activations