INDEX

Explanations

numerical values and identifiers, particularly those related to contact information and legal documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

lux

-0.16

ä¹İ

-0.15

ardash

-0.15

sdale

-0.15

plier

-0.15

Wor

-0.14

bast

-0.14

afort

-0.14

ãĤ¡

-0.14

 flex

-0.14

POSITIVE LOGITS

BF

0.16

FXML

0.15

yz

0.15

maze

0.14

 Penn

0.14

Î¬Î²

0.14

ades

0.13

BorderColor

0.13

ACA

0.13

ANGO

0.13

Activations Density 0.105%

numerical values and identifiers, particularly those related to contact information and legal documentation

No Comments

No Known Activations