© 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. 98050
    Prev
    Next
    INDEX
    Explanations

    references to possession and interactions with demons

    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
    inoa
    -0.06
    ington
    -0.06
    onia
    -0.06
    inea
    -0.06
    weeney
    -0.06
    cret
    -0.06
    burg
    -0.06
    797
    -0.06
    iche
    -0.06
    Ñĩ
    -0.06
    POSITIVE LOGITS
    dÃŃ
    0.06
    ãĥ¼ãĥĸ
    0.06
    гÑĢа
    0.06
    oft
    0.06
     Sauce
    0.06
    frauen
    0.06
    ¯u
    0.06
    (BitConverter
    0.06
    fds
    0.06
    _SDK
    0.06
    Activations Density 0.040%

    No Known Activations