© 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. 104834
    Prev
    Next
    INDEX
    Explanations

    references to the name "Joan" and related terms that indicate connection to a specific narrative or subject

    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
    izador
    -0.07
    ieux
    -0.06
    dez
    -0.06
    udes
    -0.06
    kul
    -0.06
    noc
    -0.06
    icont
    -0.06
    iva
    -0.06
    gn
    -0.06
    nar
    -0.06
    POSITIVE LOGITS
    ey
    0.07
    ep
    0.07
    _PUR
    0.07
    combe
    0.07
    enburg
    0.06
    ÙĨدÛĮ
    0.06
     xhttp
    0.06
    olk
    0.06
    eco
    0.06
    ssc
    0.06
    Activations Density 0.006%

    No Known Activations