© 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. 98426
    Prev
    Next
    INDEX
    Explanations

    aspects related to artistic inspiration

    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
    avana
    -0.08
    owler
    -0.06
    iar
    -0.06
    uala
    -0.06
    acco
    -0.06
    azio
    -0.06
    getti
    -0.06
     Dod
    -0.06
    ova
    -0.06
     arbitrary
    -0.06
    POSITIVE LOGITS
    çIJ´
    0.08
    gle
    0.07
    ÑĦик
    0.07
    iping
    0.06
    ?action
    0.06
    _impl
    0.06
     Compass
    0.06
    Ngh
    0.06
    æį·
    0.06
    _unpack
    0.06
    Activations Density 0.000%

    No Known Activations