INDEX

Explanations

terms related to recovery and healing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

-0.17

uth

-0.16

-0.15

ality

-0.15

 Affero

-0.15

ernel

-0.15

icap

-0.15

urret

-0.15

ural

-0.15

isters

-0.15

POSITIVE LOGITS

ies

0.23

 lost

0.22

IES

0.20

-from

0.20

/rest

0.19

 Lost

0.18

lost

0.18

 from

0.17

Lost

0.17

dam

0.16

Activations Density 0.038%

terms related to recovery and healing processes

No Comments

No Known Activations