INDEX

Explanations

references to legal documents or proceedings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

rak

-0.16

BJECT

-0.14

 McCartney

-0.14

 Harden

-0.14

ubat

-0.14

LEGRO

-0.14

 Bilim

-0.13

ray

-0.13

à¹Ĭ

-0.13

 Minist

-0.13

POSITIVE LOGITS

orial

0.17

lund

0.16

.opendaylight

0.15

ercul

0.14

dq

0.13

AccessException

0.13

multipart

0.13

tae

0.13

$MESS

0.13

Ob

0.13

Activations Density 0.040%

references to legal documents or proceedings

No Comments

No Known Activations