INDEX

Explanations

names of characters in a story

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

zd

-0.15

ght

-0.14

ë¨¹

-0.14

culus

-0.14

Įĵ

-0.14

ãĥĥãĥĦ

-0.14

elligent

-0.14

="__

-0.13

 bagi

-0.13

 dirig

-0.13

POSITIVE LOGITS

 soap

0.28

 Soap

0.25

soap

0.22

xml

0.21

Soap

0.20

 Coron

0.19

.xml

0.19

_xml

0.19

 storyline

0.19

 SOAP

0.18

Activations Density 0.009%

names of characters in a story

No Comments

No Known Activations