INDEX

Explanations

words associated with nationalities and geographical entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

mits

-0.15

.sax

-0.14

hetto

-0.14

ets

-0.14

pedia

-0.13

Asia

-0.13

illez

-0.13

leitung

-0.13

ion

-0.13

 Asia

-0.13

POSITIVE LOGITS

apanese

0.19

wegian

0.19

icense

0.18

merican

0.16

istani

0.16

arian

0.16

 Canadian

0.16

namese

0.15

american

0.15

 American

0.15

Activations Density 0.081%

words associated with nationalities and geographical entities

No Comments

No Known Activations