INDEX

Explanations

phrases that indicate emotional states and complex interactions between characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

áº±ng

-0.14

 Bulk

-0.14

emes

-0.13

_EST

-0.13

.parameter

-0.13

omm

-0.13

ASON

-0.13

ãĤ·ãĥ¥

-0.13

ald

-0.13

AME

-0.13

POSITIVE LOGITS

aÃ§Ãµes

0.15

clerosis

0.14

antu

0.14

ãĥ¬ãĥĥãĥĪ

0.14

URIComponent

0.13

Ø§Ø³Ùĩ

0.13

 Dagger

0.13

serializer

0.13

occo

0.13

mens

0.13

Activations Density 1.235%

phrases that indicate emotional states and complex interactions between characters

No Comments

No Known Activations