INDEX

Explanations

specific addresses and location names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Arap

-0.16

 Trib

-0.16

ahoma

-0.15

vier

-0.15

ÏĦÏģÎ¿

-0.14

 Niagara

-0.14

ampa

-0.14

ko

-0.14

ouv

-0.14

Î¬Ïģ

-0.14

POSITIVE LOGITS

 Halifax

0.36

 Nova

0.33

Nova

0.29

NS

0.26

 nova

0.25

.ns

0.25

 Dart

0.25

Hal

0.25

 Scotia

0.23

Activations Density 0.031%

specific addresses and location names

No Comments

No Known Activations