INDEX

Explanations

components and modules in code or programming-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

emme

-0.15

/Framework

-0.14

uft

-0.14

ansen

-0.14

Hem

-0.14

pector

-0.14

.framework

-0.14

dff

-0.14

ket

-0.13

uido

-0.13

POSITIVE LOGITS

.py

0.37

.js

0.34

.cpp

0.32

.php

0.26

.hpp

0.25

.html

0.25

.java

0.24

.ts

0.23

.lua

0.22

.dart

0.22

Activations Density 0.117%

components and modules in code or programming-related terms

No Comments

No Known Activations