INDEX

Explanations

references to structural integrity and secure connections in physical objects

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

iani

-0.15

_AURA

-0.14

oda

-0.14

 transparent

-0.13

 Hicks

-0.13

 shielding

-0.13

 modne

-0.13

amo

-0.13

POSITIVE LOGITS

 secure

0.34

 stable

0.30

 securely

0.28

 Secure

0.28

secure

0.28

 stability

0.28

Secure

0.27

 firm

0.27

 Firm

0.26

ç¨³

0.26

Activations Density 0.141%

references to structural integrity and secure connections in physical objects

No Comments

No Known Activations