© 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. 94682
    Prev
    Next
    INDEX
    Explanations

    locations or prominent geographic features

    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
    icity
    -0.07
    rupa
    -0.06
    egers
    -0.06
    osg
    -0.06
    еÑı
    -0.06
     Bronx
    -0.06
    ejs
    -0.06
    keterangan
    -0.06
    uml
    -0.06
    hole
    -0.06
    POSITIVE LOGITS
    talk
    0.06
    ue
    0.06
    ird
    0.06
    stead
    0.06
     Fu
    0.06
     districts
    0.06
    еÑĢÑĪ
    0.06
    ony
    0.05
    qe
    0.05
    Gatt
    0.05
    Activations Density 0.005%

    No Known Activations