INDEX

Explanations

words related to apologies and their variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

.elementAt

-0.15

PerPage

-0.14

fore

-0.14

erne

-0.14

ainty

-0.14

ermann

-0.14

 Fighters

-0.14

pile

-0.13

amt

-0.13

ank

-0.13

POSITIVE LOGITS

ap

0.23

portion

0.22

ocalyptic

0.22

Ap

0.22

PLIED

0.19

istogram

0.19

ertura

0.19

alach

0.19

pear

0.18

POINT

0.18

Activations Density 0.032%

words related to apologies and their variations

No Comments

No Known Activations