INDEX

Explanations

references to legal documents and proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Giang

-0.17

Ã©ri

-0.15

 Morg

-0.14

onte

-0.14

lemn

-0.14

 Gonzalez

-0.14

Argb

-0.13

é®®

-0.13

uve

-0.13

elen

-0.13

POSITIVE LOGITS

pendicular

0.15

upos

0.14

legen

0.14

amt

0.14

 Joanna

0.14

.um

0.14

 shall

0.14

 ÑıÐºÐ¾ÑģÑĤÑĸ

0.14

 embracing

0.14

Ø§ÙħØ§

0.14

Activations Density 0.043%

references to legal documents and proceedings

No Comments

No Known Activations