INDEX

Explanations

phrases indicating audience engagement and enjoyment in storytelling

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

æĺłçĶ»

-0.15

_DAC

-0.15

apiro

-0.15

endale

-0.14

porte

-0.14

 thiá»ĩn

-0.14

ÅĻej

-0.14

à¸¥à¸²à¸Ķ

-0.14

resco

-0.14

alle

-0.13

POSITIVE LOGITS

FRING

0.15

UBY

0.15

TestCategory

0.15

ì²ľ

0.15

undi

0.15

.camel

0.15

 Sala

0.14

ä»

0.14

quil

0.14

OTE

0.14

Activations Density 0.138%

phrases indicating audience engagement and enjoyment in storytelling

No Comments

No Known Activations