INDEX

Explanations

references to specific locations, properties, or addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

yg

-0.17

æĳĨ

-0.15

wort

-0.15

igan

-0.14

ependency

-0.14

opup

-0.14

erus

-0.13

 undermin

-0.13

ataka

-0.13

 Mattis

-0.13

POSITIVE LOGITS

 Hollywood

0.28

 Universal

0.20

ollywood

0.19

ldr

0.18

 Sunset

0.18

HOL

0.18

 Robertson

0.18

 Strip

0.17

Universal

0.16

 Griffith

0.16

Activations Density 0.043%

references to specific locations, properties, or addresses

No Comments

No Known Activations

references to specific locations, properties, or addresses

No Comments

No Known Activations