© 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. 92086
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a minimum or least amount

    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
    ãģĦãĤĭ
    -0.07
    alez
    -0.06
     than
    -0.06
    neau
    -0.06
    oug
    -0.06
    innacle
    -0.06
    er
    -0.06
    ity
    -0.06
    lov
    -0.06
    enko
    -0.06
    POSITIVE LOGITS
    inspace
    0.08
    aviest
    0.08
     amount
    0.08
    ahan
    0.08
    liest
    0.08
    ä¹ĭä¸Ģ
    0.08
    ños
    0.08
    ern
    0.07
    =min
    0.07
    amount
    0.07
    Activations Density 0.005%

    No Known Activations