© 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. 74991
    Prev
    Next
    INDEX
    Explanations

    elements related to personal circumstances and relationships

    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
    onium
    -0.07
    ádu
    -0.07
    abin
    -0.07
     defe
    -0.07
    enger
    -0.07
    icaret
    -0.07
    oger
    -0.06
    ÙIJÙij
    -0.06
    abit
    -0.06
    asket
    -0.06
    POSITIVE LOGITS
     Moines
    0.06
    ness
    0.06
     Pair
    0.06
    ensburg
    0.06
    (er
    0.06
    inee
    0.06
    nie
    0.06
    nard
    0.06
    602
    0.05
    swick
    0.05
    Activations Density 0.032%

    No Known Activations