© 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. 61822
    Prev
    Next
    INDEX
    Explanations

    terms related to suicide and suicidal ideation

    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
    ness
    -0.08
    ning
    -0.08
     मद
    -0.07
    неÑģÑĤи
    -0.07
    uplic
    -0.07
    gies
    -0.07
    ospace
    -0.07
    lier
    -0.07
    Deg
    -0.07
    roje
    -0.07
    POSITIVE LOGITS
     prevention
    0.08
    ously
    0.07
    /self
    0.07
     Prevention
    0.07
    çİĩ
    0.06
    ois
    0.06
     rate
    0.06
    lectric
    0.06
     hút
    0.06
     attempt
    0.06
    Activations Density 0.006%

    No Known Activations