© 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. 93023
    Prev
    Next
    INDEX
    Explanations

    references to age statistics and demographic data

    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
    ayer
    -0.06
    igli
    -0.06
    START
    -0.06
    ierarchy
    -0.06
    AYER
    -0.06
    kus
    -0.06
    ç§į
    -0.06
    allo
    -0.05
    afa
    -0.05
     cockpit
    -0.05
    POSITIVE LOGITS
    umlu
    0.07
     Feinstein
    0.07
    ãĤ¤ãĤº
    0.07
    Ä©nh
    0.06
     Sampler
    0.06
    å¹´é¾Ħ
    0.06
    aklı
    0.06
     rám
    0.06
    CodeAt
    0.06
    à¹Ģà¸Ńà¸ĩ
    0.06
    Activations Density 0.001%

    No Known Activations