INDEX

Explanations

references to specific legal and academic topics

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

Å¡ov

-0.18

imm

-0.15

oe

-0.14

oky

-0.14

 McKin

-0.14

.ie

-0.14

tz

-0.14

 Shak

-0.13

Nim

-0.13

ASI

-0.13

POSITIVE LOGITS

vida

0.15

Éµ

0.15

OptionsResolver

0.14

Ì

0.14

roid

0.14

criptors

0.14

.scalablytyped

0.14

å¾ħ

0.14

ipur

0.13

isman

0.13

Activations Density 0.195%

references to specific legal and academic topics

No Comments

No Known Activations