INDEX

Explanations

names of notable individuals, particularly those referenced or involved in a historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 blah

-0.15

Mum

-0.14

 scope

-0.14

ollen

-0.14

Mom

-0.14

ea

-0.14

ossa

-0.14

Ä±lÄ±Ã§

-0.13

ãĤ¤ãĥī

-0.13

lli

-0.13

POSITIVE LOGITS

ieten

0.16

ãĤ¹ãĤ«

0.14

Ø§Ø¦ÙĬØ©

0.14

æķ·

0.14

á»ĥm

0.13

istrovstvÃŃ

0.13

stakes

0.13

utar

0.13

ãĤ¹ãĤ¿ãĥ¼

0.13

quoise

0.13

Activations Density 0.000%

names of notable individuals, particularly those referenced or involved in a historical context

No Comments

No Known Activations