© 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. 38875
    Prev
    Next
    INDEX
    Explanations

    negative and dangerous associations related to people

    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
     имÑĥ
    -0.07
     ___
    -0.07
    ore
    -0.07
    ndef
    -0.07
    ienes
    -0.06
    .UnitTesting
    -0.06
    ê¸Ģ
    -0.06
     ______
    -0.06
    ollapsed
    -0.06
    ros
    -0.06
    POSITIVE LOGITS
    ichen
    0.07
    .Utc
    0.07
    awe
    0.07
    اÙĬÙĦ
    0.07
    dden
    0.07
    айÑĤ
    0.07
    adal
    0.07
    ạ
    0.07
     ÑģлÑĥÑĩ
    0.07
    ÙĪزÙĩ
    0.06
    Activations Density 0.060%

    No Known Activations