INDEX

Explanations

references to ownership or possession

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

atti

-0.17

lea

-0.16

pei

-0.14

lights

-0.14

acro

-0.14

ynes

-0.14

itudes

-0.14

learner

-0.13

 Realt

-0.13

micro

-0.13

POSITIVE LOGITS

SELF

0.20

 yourself

0.18

nger

0.17

opic

0.16

anmar

0.16

opia

0.15

ocu

0.15

ths

0.15

åĢĳ

0.15

 guys

0.15

Activations Density 0.191%

references to ownership or possession

No Comments

No Known Activations