© 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. 105151
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships and genealogical details

    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
    ìĪ
    -0.07
    aab
    -0.07
    enberg
    -0.07
    YC
    -0.07
    άÏĤ
    -0.07
    تاب
    -0.07
    APA
    -0.07
    subcategory
    -0.07
    عدد
    -0.07
     offsetof
    -0.06
    POSITIVE LOGITS
     gene
    0.07
     records
    0.07
     reversal
    0.07
     revers
    0.06
    kommen
    0.06
     Vital
    0.06
     record
    0.06
     vital
    0.06
     reversed
    0.06
     census
    0.06
    Activations Density 0.047%

    No Known Activations