© 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. 9-LLAMASCOPE-RES-131K
    11. 94593
    Prev
    Next
    INDEX
    Explanations

    instances of possessive forms

    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
    fid
    -0.07
    ÄĽÅ¾
    -0.07
    dee
    -0.07
    بط
    -0.06
    ynos
    -0.06
    ÑĢабоÑĤ
    -0.06
    sworth
    -0.06
    iez
    -0.06
    MOTE
    -0.06
    nder
    -0.06
    POSITIVE LOGITS
    isi
    0.06
    .SizeF
    0.06
     $__
    0.06
     Cherry
    0.06
    ables
    0.06
    iben
    0.06
    .GraphicsUnit
    0.06
     impl
    0.06
    ernity
    0.06
     Progress
    0.06
    Activations Density 0.021%

    No Known Activations