INDEX

Explanations

programming-related code, elements, and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eldorf

-0.20

ften

-0.18

rawer

-0.16

 Bridges

-0.16

oji

-0.15

arb

-0.15

 Ð·Ð°ÑģÑĤ

-0.15

 Dash

-0.15

verb

-0.15

Fog

-0.15

POSITIVE LOGITS

.ua

0.15

iddy

0.15

ograph

0.14

 Forces

0.13

ica

0.13

bum

0.13

 âĸĪâĸĪ

0.13

orphism

0.13

ood

0.13

apt

0.13

Activations Density 0.763%

programming-related code, elements, and data structures

No Comments

No Known Activations