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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 39322
    Prev
    Next
    INDEX
    Explanations

    linguistic variations and morphological forms of words

    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
    itto
    -0.08
    ÚĨÙĩ
    -0.08
    ÑĢÑĥж
    -0.07
    âĻ¡
    -0.07
    WER
    -0.07
    bt
    -0.07
    iness
    -0.06
     dÄĽt
    -0.06
    /people
    -0.06
    Ỽp
    -0.06
    POSITIVE LOGITS
    mente
    0.10
    ly
    0.07
    à¹Ĩ
    0.07
    erable
    0.07
    ément
    0.07
    gado
    0.06
     Hundred
    0.06
    ely
    0.06
    oad
    0.06
    ÑģÑĤÑİ
    0.06
    Activations Density 0.082%

    No Known Activations