INDEX

Explanations

emotional reactions and interactions among characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã´ng

-0.19

insky

-0.18

ÑĶÑĪ

-0.16

_WRAPPER

-0.14

issance

-0.14

headline

-0.14

ystate

-0.14

iky

-0.13

utilus

-0.13

andr

-0.13

POSITIVE LOGITS

ÐºÐµÑĤ

0.15

ÏĦÏĮ

0.14

DDL

0.14

adx

0.14

 movement

0.13

.virtual

0.13

onica

0.13

 Eastern

0.13

InnerText

0.13

olle

0.13

Activations Density 0.323%

emotional reactions and interactions among characters

No Comments

No Known Activations