© 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. 15-LLAMASCOPE-RES-131K
    11. 87799
    Prev
    Next
    INDEX
    Explanations

    requests for contacting individuals or organizations for more information

    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
    .typ
    -0.07
    Bonjour
    -0.07
    upp
    -0.07
    ippers
    -0.06
    _simps
    -0.06
    esser
    -0.06
     ActionTypes
    -0.06
    iox
    -0.06
    uckets
    -0.06
    osto
    -0.06
    POSITIVE LOGITS
    idebar
    0.07
     cra
    0.07
     either
    0.06
    popover
    0.06
     retire
    0.06
     Ng
    0.06
    hdl
    0.06
     Bil
    0.06
     nearest
    0.06
    anggal
    0.06
    Activations Density 0.009%

    No Known Activations