© 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. 61827
    Prev
    Next
    INDEX
    Explanations

    references to days of the week and associated activities

    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
     Cah
    -0.07
    .dsl
    -0.07
    REA
    -0.07
    å¿ł
    -0.07
    Äı
    -0.06
    esa
    -0.06
    页éĿ¢åŃĺæ¡£å¤ĩ份
    -0.06
    aven
    -0.06
    WSC
    -0.06
    æī±
    -0.06
    POSITIVE LOGITS
    -toggler
    0.07
    úsqueda
    0.06
    iram
    0.06
    _tD
    0.06
     Show
    0.06
     Andersen
    0.05
    _mE
    0.05
    ampler
    0.05
    antz
    0.05
    _mB
    0.05
    Activations Density 0.004%

    No Known Activations