© 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. 86354
    Prev
    Next
    INDEX
    Explanations

    references to Facebook and its related services and competitors

    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
    ãİ
    -0.07
    iв
    -0.07
    $MESS
    -0.07
    _DEPRECATED
    -0.07
    esor
    -0.06
    resi
    -0.06
    ाà¤ĩम
    -0.06
    rollo
    -0.06
    ÑĢÑĸÑĪ
    -0.06
    еÐ
    -0.06
    POSITIVE LOGITS
     founder
    0.08
     parent
    0.07
    mania
    0.07
    åħ¬åı¸
    0.06
    kea
    0.06
    GLOBALS
    0.06
     Corporation
    0.06
    .setColumn
    0.06
     unspecified
    0.06
     hind
    0.06
    Activations Density 0.023%

    No Known Activations