INDEX

Explanations

words related to engagement or involvement in collective activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

du

-0.23

ro

-0.23

ness

-0.20

nya

-0.19

no

-0.19

ror

-0.18

nu

-0.18

nak

-0.18

wor

-0.18

ling

-0.18

POSITIVE LOGITS

ffset

0.31

'nun

0.27

’nun

0.27

eur

0.24

vertime

0.24

LOGY

0.23

xford

0.23

eus

0.23

xygen

0.22

Activations Density 0.127%

words related to engagement or involvement in collective activities

No Comments

No Known Activations