INDEX

Explanations

expressions of personal experience and support 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 @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

evin

-0.16

ucer

-0.16

erli

-0.15

edes

-0.15

eniable

-0.15

ÑĤÐ¾Ñĩ

-0.15

 telefon

-0.15

cies

-0.14

.ArgumentParser

-0.14

_stride

-0.14

POSITIVE LOGITS

 others

0.26

 Others

0.24

Others

0.23

 sharing

0.23

others

0.20

 Sharing

0.20

 useful

0.19

 warning

0.18

 fellow

0.18

Ä±l

0.17

Activations Density 0.146%

expressions of personal experience and support in narratives

No Comments

No Known Activations