INDEX

Explanations

expressions of personal or collective emotions and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ided

-0.20

rava

-0.18

uppy

-0.18

ity

-0.17

enaire

-0.17

linky

-0.16

sWith

-0.16

dy

-0.16

reated

-0.16

ogle

-0.15

POSITIVE LOGITS

lessly

0.30

less

0.24

making

0.21

chal

0.20

ful

0.19

LESS

0.19

fully

0.18

0.17

ible

0.17

idon

0.17

Activations Density 0.016%

expressions of personal or collective emotions and experiences

No Comments

No Known Activations