INDEX

Explanations

terms related to masks and their impact on health and well-being

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stag

-0.17

oy

-0.15

lim

-0.15

icha

-0.14

adio

-0.14

 Carpet

-0.14

Ged

-0.13

assic

-0.13

à¹Īà¸²à¸¢

-0.13

_lim

-0.13

POSITIVE LOGITS

 mask

0.61

 masks

0.60

 Masks

0.55

 Mask

0.52

-mask

0.50

Mask

0.49

mask

0.49

 MASK

0.48

.mask

0.46

_mask

0.44

Activations Density 0.055%

terms related to masks and their impact on health and well-being

No Comments

No Known Activations