INDEX

Explanations

names of countries and cities, particularly those in Canada and the USA

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aurus

-0.18

oub

-0.15

ews

-0.15

egra

-0.14

Pik

-0.14

lara

-0.14

 Mutual

-0.14

 treff

-0.14

ÑĦÑĤ

-0.14

Pek

-0.14

POSITIVE LOGITS

weit

0.20

-flag

0.18

nesia

0.15

 Henri

0.15

 flag

0.15

flag

0.15

 Brewers

0.14

iyas

0.14

FLAG

0.14

minor

0.14

Activations Density 0.106%

names of countries and cities, particularly those in Canada and the USA

No Comments

No Known Activations