INDEX

Explanations

programming-related classes and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

kud

-0.16

yb

-0.15

-0.14

ombres

-0.13

 Dickinson

-0.13

udd

-0.13

oc

-0.13

POSITIVE LOGITS

 extends

0.33

 extend

0.24

 extending

0.21

 implements

0.20

extends

0.19

 :↵

0.19

 {↵↵

0.19

0.18

 :↵↵

0.18

 extent

0.17

Activations Density 0.033%

programming-related classes and services

No Comments

No Known Activations