INDEX

Explanations

references to statistics and numerical data

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

iac

-0.15

 Castro

-0.15

GHC

-0.15

neh

-0.14

NavController

-0.14

à¸Ļà¸¡

-0.14

 Pods

-0.14

.Singleton

-0.14

rome

-0.14

ant

-0.14

POSITIVE LOGITS

 Nigeria

0.32

 Nigerian

0.30

 nigeria

0.25

 Niger

0.24

 Lagos

0.23

 Federal

0.21

 Haus

0.21

igeria

0.21

Federal

0.18

 federal

0.18

Activations Density 0.118%

references to statistics and numerical data

No Comments

No Known Activations