INDEX

Explanations

technical terms and references related to programming and scaling functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

fsp

-0.16

obao

-0.15

uition

-0.14

otte

-0.14

xmm

-0.14

 Ð¾Ð±Ð»Ð°

-0.14

lfw

-0.14

 squeeze

-0.14

omite

-0.13

UIL

-0.13

POSITIVE LOGITS

Tk

0.28

Tk

0.28

tk

0.28

(tk

0.27

tk

0.26

 tkinter

0.26

TK

0.24

Tcl

0.24

TK

0.24

.tk

0.23

Activations Density 0.018%

technical terms and references related to programming and scaling functions

No Comments

No Known Activations