INDEX

Explanations

instances of emotional and physical actions or states expressed in the narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

Dud

-0.16

ashtra

-0.15

wald

-0.15

Wyn

-0.14

 superst

-0.14

 reservation

-0.14

arkin

-0.14

camp

-0.14

 intim

-0.14

POSITIVE LOGITS

_Tis

0.18

ume

0.17

ozor

0.16

DialogTitle

0.15

	templateUrl

0.15

ä¹ĥ

0.15

rase

0.15

_Osc

0.15

urn

0.15

VERTISEMENT

0.14

Activations Density 0.162%

instances of emotional and physical actions or states expressed in the narrative

No Comments

No Known Activations