INDEX

Explanations

specific names or identifiers related to events, organizations, or branded entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ansas

-0.15

ijkstra

-0.15

ropa

-0.15

ownik

-0.14

abbage

-0.14

atcher

-0.13

agi

-0.13

.edu

-0.13

atory

-0.13

igslist

-0.13

POSITIVE LOGITS

ï»¿↵

0.14

lili

0.14

Ã¡zev

0.14

 Ø§ÙĦØ±ÙħØ²ÙĬØ©

0.13

isphere

0.13

yb

0.13

Ú¯Ø§ÙĩÛĮ

0.13

edith

0.13

edir

0.13

Siz

0.13

Activations Density 0.306%

specific names or identifiers related to events, organizations, or branded entities

No Comments

No Known Activations