© 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. 63209
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-ownership and personal rights

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    engo
    -0.06
    bote
    -0.06
    unj
    -0.06
    lass
    -0.06
     Jensen
    -0.06
    ella
    -0.06
    wei
    -0.06
    ÑĨеÑĢ
    -0.06
    -wide
    -0.06
    conte
    -0.06
    POSITIVE LOGITS
    /self
    0.17
     Self
    0.12
    Self
    0.11
    (Self
    0.11
     self
    0.10
     SELF
    0.10
    SELF
    0.10
    self
    0.09
    ,self
    0.09
    -self
    0.09
    Activations Density 0.031%

    No Known Activations