© 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. 15-LLAMASCOPE-RES-131K
    11. 87361
    Prev
    Next
    INDEX
    Explanations

    instances of the word "frame" and related variations, indicating a focus on how issues and requests are presented or contextualized

    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
     kostenlose
    -0.07
     zemi
    -0.06
    ialis
    -0.06
    åijĺ
    -0.06
    åĵ¡
    -0.06
    etik
    -0.06
    _APPS
    -0.06
    /people
    -0.06
    ียà¸Ķ
    -0.06
    ---</
    -0.06
    POSITIVE LOGITS
    ahlen
    0.08
     Fram
    0.08
     ÑĢам
    0.07
    .Framework
    0.07
    arg
    0.07
    :frame
    0.07
    ettle
    0.06
    arch
    0.06
    osi
    0.06
    amientos
    0.06
    Activations Density 0.012%

    No Known Activations