INDEX

Explanations

terms related to characters and their roles in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ã²ng

-0.16

luk

-0.16

reater

-0.15

isson

-0.15

ä¼

-0.15

ackage

-0.14

 Temple

-0.14

apon

-0.14

erring

-0.14

į¨

-0.14

POSITIVE LOGITS

 late

0.28

Nam

0.27

late

0.24

Adj

0.22

spr

0.21

Nam

0.21

Spr

0.20

wort

0.19

spr

0.19

 Late

0.19

Activations Density 0.020%

terms related to characters and their roles in a narrative

No Comments

No Known Activations