INDEX

Explanations

linguistic elements related to narrative or storytelling constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ekim

-0.16

ients

-0.15

Ð¿Ð¸

-0.15

iento

-0.15

 Ø§ÙĦØ¹Ùħ

-0.14

yb

-0.14

oref

-0.14

:::::

-0.14

allis

-0.14

POSITIVE LOGITS

.Gen

0.17

iÃŁ

0.15

eler

0.15

erner

0.14

alone

0.14

#ac

0.14

 Bundy

0.14

via

0.14

iga

0.13

 rapid

0.13

Activations Density 0.064%

linguistic elements related to narrative or storytelling constructs

No Comments

No Known Activations