INDEX

Explanations

references to the concept of "wild" in various contexts, including emotions, settings, or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ilda

-0.18

yonel

-0.17

idar

-0.16

abel

-0.16

.scalablytyped

-0.14

edis

-0.14

imos

-0.14

 Morr

-0.14

asje

-0.14

imiz

-0.14

POSITIVE LOGITS

ness

0.20

tip

0.15

sam

0.15

 Throne

0.14

RAP

0.14

iferay

0.14

tips

0.14

è¿¹

0.14

antro

0.14

Activations Density 0.012%

references to the concept of "wild" in various contexts, including emotions, settings, or characters

No Comments

No Known Activations