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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 125401
    Prev
    Next
    INDEX
    Explanations

    mentions of the city of Leeds

    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
    isky
    -0.07
    umas
    -0.07
    isk
    -0.07
    uesta
    -0.07
    é£İéĻ©
    -0.07
     ÑĢиз
    -0.06
    "struct
    -0.06
    ISK
    -0.06
    uela
    -0.06
    onas
    -0.06
    POSITIVE LOGITS
     tow
    0.08
    imest
    0.07
    pii
    0.07
    .Glide
    0.06
    dings
    0.06
    arend
    0.06
    mesh
    0.06
    Ïĥιμο
    0.06
    opia
    0.06
    cia
    0.06
    Activations Density 0.001%

    No Known Activations