© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 38548
    Prev
    Next
    INDEX
    Explanations

    terms related to privacy or private spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iesz
    -0.08
    Wunused
    -0.07
     Niet
    -0.07
    ÐĺТ
    -0.07
    ÎŁÎ
    -0.07
    .chunk
    -0.07
    iban
    -0.07
    lok
    -0.07
    ä¸īä¸ī
    -0.07
    jar
    -0.07
    POSITIVE LOGITS
    /private
    0.09
    /public
    0.07
     exclusive
    0.07
    exclusive
    0.07
    -exclusive
    0.06
     Exclusive
    0.06
    -ish
    0.06
     sit
    0.06
     space
    0.06
    oom
    0.06
    Activations Density 0.005%

    No Known Activations