INDEX

Explanations

possessive pronouns and phrases indicating ownership or belonging

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

gree

-0.15

ooks

-0.15

ioneer

-0.15

indle

-0.14

eden

-0.14

anna

-0.14

enden

-0.14

mousemove

-0.14

 Conway

-0.14

 INTERRU

-0.14

POSITIVE LOGITS

 fault

0.27

 Fault

0.25

 undo

0.24

Fault

0.21

fault

0.21

 contribution

0.19

 Achilles

0.19

 Contribution

0.19

 responsibility

0.19

cue

0.17

Activations Density 0.109%

possessive pronouns and phrases indicating ownership or belonging

No Comments

No Known Activations