INDEX

Explanations

phrases related to tranquility and escape

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

anca

-0.15

odem

-0.15

 skal

-0.14

alar

-0.14

aget

-0.14

 Rede

-0.14

afil

-0.14

Persistence

-0.13

/il

-0.13

PÅĻed

-0.13

POSITIVE LOGITS

 peace

0.47

peace

0.37

ser

0.36

 Peace

0.33

 peaceful

0.33

 tranqu

0.30

 calm

0.29

 relaxation

0.29

Peace

0.29

 Tran

0.28

Activations Density 0.320%

phrases related to tranquility and escape

No Comments

No Known Activations