INDEX

Explanations

technical terms and file references related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

upo

-0.15

ÙģØª

-0.14

 Flake

-0.14

olang

-0.14

olen

-0.14

 Hale

-0.14

gettext

-0.13

 sentence

-0.13

')."

-0.13

Disposed

-0.13

POSITIVE LOGITS

.txt

0.35

.xml

0.30

.json

0.26

.png

0.23

.js

0.23

.csv

0.22

.py

0.22

.md

0.22

.yml

0.21

.html

0.21

Activations Density 0.140%

technical terms and file references related to programming and software development

No Comments

No Known Activations