INDEX

Explanations

references to characters and their relationships in narratives

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

PA

-0.15

Ð²Ð°Ð½Ð¾Ð²

-0.15

sko

-0.14

ä¸Ī

-0.14

ungan

-0.14

abee

-0.14

ÑĢÐ¾Ð²Ð¸Ñĩ

-0.14

akash

-0.14

uteur

-0.14

POSITIVE LOGITS

 Sans

0.38

 Roose

0.32

Cer

0.32

Ary

0.31

Ser

0.31

 Jaime

0.31

Tyr

0.29

 Bran

0.29

Sans

0.29

 Rams

0.27

Activations Density 0.001%

references to characters and their relationships in narratives

No Comments

No Known Activations