INDEX

Explanations

references to specific aspects or elements of characters and storytelling 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

Ø¹ÙĨ

-0.15

owitz

-0.15

ngo

-0.14

íĭ°

-0.14

nock

-0.14

vid

-0.13

ungan

-0.13

áº©u

-0.13

 Suche

-0.13

MITTED

-0.13

POSITIVE LOGITS

ior

0.20

 thing

0.18

Calibri

0.14

(:,:,

0.14

Cls

0.13

Ã¼re

0.13

uler

0.13

isto

0.13

 elaborate

0.13

 Klein

0.13

Activations Density 0.117%

references to specific aspects or elements of characters and storytelling in narratives

No Comments

No Known Activations