© 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. 2723
    Prev
    Next
    INDEX
    Explanations

    names and terms associated with people and their relationships

    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
    fld
    -0.07
    اÙĦد
    -0.07
    edl
    -0.06
     kå
    -0.06
     nhân
    -0.06
    ça
    -0.06
    ë¡Ģ
    -0.06
    >window
    -0.06
    ứa
    -0.06
     Bene
    -0.06
    POSITIVE LOGITS
    iram
    0.06
    xious
    0.06
    ienie
    0.06
    .ResponseBody
    0.05
    aval
    0.05
    v
    0.05
    lope
    0.05
     Eph
    0.05
    ienia
    0.05
    alore
    0.05
    Activations Density 0.054%

    No Known Activations