© 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. 87039
    Prev
    Next
    INDEX
    Explanations

    references to everyday actions and objects related to basic needs

    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
     overall
    -0.07
    ables
    -0.06
     with
    -0.06
    ady
    -0.06
    ãģĵãģ¨ãģ¯
    -0.06
     layer
    -0.06
     (
    -0.06
     everything
    -0.06
    AUSE
    -0.06
    alat
    -0.06
    POSITIVE LOGITS
    ottie
    0.07
    /*č↵
    0.07
    .dep
    0.07
    kker
    0.07
    .CV
    0.07
    oggler
    0.07
    ØŃداث
    0.07
    //{{
    0.07
     Clarkson
    0.07
    BYTES
    0.07
    Activations Density 0.030%

    No Known Activations