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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 budgets

-0.18

 Budget

-0.17

 budget

-0.16

budget

-0.15

apt

-0.15

loa

-0.15

á»¥

-0.15

Budget

-0.15

 Proud

-0.14

 Skull

-0.14

POSITIVE LOGITS

toi

0.16

ê·

0.15

ansen

0.15

ãģ¯ãģĦ

0.15

azzi

0.15

stre

0.14

uvo

0.14

à¸Ńà¸Ń

0.14

 Shepard

0.14

achen

0.14

Activations Density 0.155%

references to ownership or possession

No Comments

No Known Activations