INDEX

Explanations

references to online articles or stories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

âĢ¦

-0.15

NPR

-0.14

on

-0.14

 hood

-0.14

mez

-0.14

ught

-0.14

gen

-0.14

éĩİ

-0.14

 Fabric

-0.14

POSITIVE LOGITS

ëŀ

0.16

ãĥ³ãĥĩ

0.15

/REC

0.15

omik

0.15

 Monsters

0.15

#ad

0.15

Ø§Ø±Ø´

0.15

jes

0.14

ocs

0.14

pector

0.14

Activations Density 0.004%

references to online articles or stories

No Comments

No Known Activations