INDEX

Explanations

emotional states and themes of personal introspection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

lied

-0.17

.ibatis

-0.16

loff

-0.15

,readonly

-0.15

uled

-0.15

ÙħØ¨Ø±

-0.15

åĲī

-0.14

ëĦĲ

-0.14

osate

-0.14

icana

-0.14

POSITIVE LOGITS

ness

0.42

fulness

0.41

iness

0.40

iveness

0.38

ality

0.36

liness

0.36

lessness

0.35

ity

0.32

ism

0.31

NESS

0.30

Activations Density 0.203%

emotional states and themes of personal introspection

No Comments

No Known Activations