© 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. 92809
    Prev
    Next
    INDEX
    Explanations

    incidents involving legal issues and mental health

    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
    @student
    -0.06
    .Classes
    -0.06
    ASI
    -0.06
     Chat
    -0.06
    otty
    -0.06
    NullOr
    -0.06
     Armen
    -0.06
    aida
    -0.06
     Cox
    -0.06
     Ark
    -0.06
    POSITIVE LOGITS
    resa
    0.08
    кав
    0.08
    lek
    0.08
    ango
    0.07
    roid
    0.07
    /Typography
    0.07
    vic
    0.07
    andles
    0.07
    -picture
    0.07
    agli
    0.06
    Activations Density 0.016%

    No Known Activations