© 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. 9-LLAMASCOPE-RES-131K
    11. 96677
    Prev
    Next
    INDEX
    Explanations

    references to tax obligations and financial liabilities

    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
     onto
    -0.06
    lew
    -0.06
    astes
    -0.06
    pose
    -0.06
    iks
    -0.06
     shadow
    -0.05
    acades
    -0.05
    pill
    -0.05
    262
    -0.05
     Housing
    -0.05
    POSITIVE LOGITS
    _INITIALIZER
    0.07
    мена
    0.07
    ÙĬÙĨÙĩ
    0.07
    عا
    0.07
    аÑĢÑĤам
    0.07
    ustr
    0.07
    BOOT
    0.07
    Äĩe
    0.07
    iji
    0.07
    utc
    0.07
    Activations Density 0.009%

    No Known Activations