INDEX

Explanations

instances of the word "Ind" and its variations, indicating a focus on topics related to indigenous peoples

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odos

-0.15

ysi

-0.15

avn

-0.15

illance

-0.14

Ø¦Ø©

-0.14

bling

-0.14

blind

-0.14

imson

-0.14

alth

-0.14

æĮ¯ãĤĬ

-0.14

POSITIVE LOGITS

ind

0.21

Ind

0.21

istinguish

0.18

icators

0.18

ians

0.17

ustrial

0.17

igenous

0.16

eterminate

0.16

igo

0.15

ones

0.15

Activations Density 0.018%

instances of the word "Ind" and its variations, indicating a focus on topics related to indigenous peoples

No Comments

No Known Activations