INDEX

Explanations

mentions of the word "feeling" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eson

-0.17

pio

-0.16

raith

-0.16

iesel

-0.15

reon

-0.15

fahren

-0.15

fried

-0.15

fp

-0.15

/hash

-0.14

ieg

-0.14

POSITIVE LOGITS

Fe

0.31

fe

0.30

Fe

0.27

(fe

0.25

-fe

0.24

bruary

0.23

.fe

0.22

igned

0.22

FE

0.20

fe

0.19

Activations Density 0.016%

mentions of the word "feeling" in various contexts

No Comments

No Known Activations