INDEX

Explanations

references to various forms of public transportation

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

aires

-0.19

-0.17

eer

-0.17

egra

-0.16

hill

-0.15

 nerve

-0.15

ustin

-0.15

isÃ©

-0.15

zsche

-0.15

unnel

-0.14

POSITIVE LOGITS

queda

0.23

inness

0.23

loads

0.22

INESS

0.21

(es

0.20

load

0.17

ļ

0.17

inese

0.16

INES

0.16

iens

0.16

Activations Density 0.015%

references to various forms of public transportation

No Comments

No Known Activations