© 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. 63148
    Prev
    Next
    INDEX
    Explanations

    possessive forms related to various concepts or entities

    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
     roughly
    -0.07
    556
    -0.06
     afore
    -0.06
    887
    -0.06
     belongings
    -0.06
     sokak
    -0.06
    PermissionsResult
    -0.06
    376
    -0.06
    idelberg
    -0.06
    ìĺĢ
    -0.06
    POSITIVE LOGITS
    agini
    0.07
    omu
    0.07
    emaker
    0.07
    jišť
    0.07
    vÄĽÅĻ
    0.07
    ayout
    0.07
    (Source
    0.07
    ¯
    0.07
    Äįin
    0.07
    بت
    0.06
    Activations Density 0.034%

    No Known Activations