© 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 EvalsExportsAPI 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. 125630
    Prev
    Next
    INDEX
    Explanations

    terms related to property appraisal and valuation

    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
    ality
    -0.08
    kla
    -0.07
    lam
    -0.07
    ergy
    -0.07
     à¹Ĩ
    -0.07
    ainty
    -0.06
    OP
    -0.06
    elah
    -0.06
    -gnu
    -0.06
    fat
    -0.06
    POSITIVE LOGITS
    iston
    0.07
     Shiv
    0.07
    inger
    0.07
    Ñīик
    0.07
    inged
    0.07
    DonaldTrump
    0.07
    227
    0.07
    MENT
    0.07
    ÚĨÛĮ
    0.07
    ickle
    0.06
    Activations Density 0.002%

    No Known Activations