© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96332
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and possessive forms of nouns

    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
    ito
    -0.06
     Mend
    -0.06
     Mond
    -0.06
    hu
    -0.06
     Sat
    -0.06
    opp
    -0.06
    amac
    -0.06
    лÑĮ
    -0.06
    anny
    -0.06
    åĦĢ
    -0.06
    POSITIVE LOGITS
    æĹĹ
    0.08
    _interfaces
    0.07
     Flags
    0.07
    .Persistent
    0.07
    chron
    0.07
    zych
    0.07
    ensibly
    0.07
    taj
    0.07
    à¹Ģà¸ī
    0.07
    >,</
    0.07
    Activations Density 0.037%

    No Known Activations