INDEX

Explanations

references to coding and software development concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

unde

-0.19

raj

-0.16

arih

-0.15

.Java

-0.15

oten

-0.14

emoc

-0.14

.kotlin

-0.14

Äįku

-0.14

/perl

-0.14

antan

-0.14

POSITIVE LOGITS

 Rahmen

0.17

ounced

0.15

/Users

0.15

ORM

0.15

Bundle

0.15

ering

0.14

zk

0.14

Ð·Ð¸

0.14

 bundle

0.14

din

0.14

Activations Density 0.017%

references to coding and software development concepts

No Comments

No Known Activations