© 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. 9-LLAMASCOPE-RES-131K
    11. 97780
    Prev
    Next
    INDEX
    Explanations

    references to the Nauru community and issues related to gender-based violence

    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
    erton
    -0.06
     qu
    -0.06
    urga
    -0.06
    åĨĨ
    -0.06
    abant
    -0.06
    ripe
    -0.06
    china
    -0.06
    ocio
    -0.06
    elligent
    -0.05
     unc
    -0.05
    POSITIVE LOGITS
    ãĤ¸ãĤ¢
    0.07
    _ctl
    0.07
     ÅĻÃŃj
    0.07
    bÃŃ
    0.07
    лÑı
    0.06
    agan
    0.06
    ικα
    0.06
    _collections
    0.06
    _TIM
    0.06
    aso
    0.06
    Activations Density 0.005%

    No Known Activations