© 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. 104989
    Prev
    Next
    INDEX
    Explanations

    elements related to character-driven narratives and scripted routines

    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
    ucha
    -0.06
     quality
    -0.06
    ucus
    -0.06
     Kir
    -0.06
     loose
    -0.06
     Licht
    -0.06
    419
    -0.06
    ien
    -0.05
    lig
    -0.05
    egan
    -0.05
    POSITIVE LOGITS
    Interstitial
    0.07
    vil
    0.07
    .getOwnProperty
    0.07
    Bezier
    0.07
    еÑĢалÑĮ
    0.07
    serter
    0.07
    datable
    0.07
    ÑģÑĤоÑı
    0.07
    senal
    0.07
    ktop
    0.07
    Activations Density 0.016%

    No Known Activations