INDEX

Explanations

names of people or organizations

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

-0.16

-0.15

ç£

-0.15

nan

-0.14

ÐµÑĢÑĤÐ¸

-0.14

'])){

-0.14

inv

-0.14

dif

-0.13

indle

-0.13

 sharp

-0.13

POSITIVE LOGITS

NetMessage

0.18

ifo

0.18

agit

0.16

igmoid

0.16

Ð»Ð¾Ð²Ð°

0.15

inerary

0.15

Mey

0.15

imed

0.15

ulaire

0.14

unger

0.14

Activations Density 0.056%

names of people or organizations

No Comments

No Known Activations