© 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 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. 17-LLAMASCOPE-RES-131K
    11. 29339
    Prev
    Next
    INDEX
    Explanations

    attributes and values associated with HTML input elements

    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
    .GridColumn
    -0.07
    íĨłíĨł
    -0.07
    vasion
    -0.07
    ÑĢаÑĩ
    -0.07
     Namen
    -0.07
    ium
    -0.07
    å¤ķ
    -0.07
    .PO
    -0.06
    usat
    -0.06
    $header
    -0.06
    POSITIVE LOGITS
    odash
    0.07
    utches
    0.07
    IDX
    0.06
    ="
    0.06
     Tra
    0.06
    =”
    0.06
    ieux
    0.06
    zew
    0.06
     other
    0.06
    æĥħ
    0.06
    Activations Density 0.004%

    No Known Activations