INDEX

Explanations

emotional attributes and moral judgments related to characters and actions 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 @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

rego

-0.18

kara

-0.16

oro

-0.15

lobs

-0.14

 Welch

-0.14

.bid

-0.14

aday

-0.14

stag

-0.14

echn

-0.14

.DataType

-0.14

POSITIVE LOGITS

apus

0.17

æĥħ

0.14

tees

0.14

TOOLS

0.14

Ð¸Ð¶

0.14

/MPL

0.14

-kit

0.14

dal

0.14

McN

0.14

 Dream

0.13

Activations Density 1.010%

emotional attributes and moral judgments related to characters and actions in narratives

No Comments

No Known Activations