© 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. 123914
    Prev
    Next
    INDEX
    Explanations

    references to "this" or "post" in varying contexts

    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
    omy
    -0.07
    ohn
    -0.07
    olv
    -0.06
     consum
    -0.06
    μά
    -0.06
    agem
    -0.06
    ãģĹãĤĩ
    -0.06
    /*č↵
    -0.06
    FormItem
    -0.06
    /renderer
    -0.06
    POSITIVE LOGITS
    mando
    0.07
     occasion
    0.07
    inker
    0.06
    occasion
    0.06
    fern
    0.06
     presente
    0.06
    bz
    0.06
     case
    0.06
    esar
    0.06
    ercicio
    0.06
    Activations Density 0.018%

    No Known Activations