© 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. 57898
    Prev
    Next
    INDEX
    Explanations

    statements related to political criticism or accusations

    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
    iban
    -0.07
     kå
    -0.07
    hoff
    -0.07
    ematik
    -0.06
    _simps
    -0.06
    WebpackPlugin
    -0.06
    ellen
    -0.06
    omm
    -0.06
    à¥ĭफ
    -0.06
    outil
    -0.06
    POSITIVE LOGITS
    à¹Ĥà¸ģ
    0.07
    925
    0.07
    uj
    0.06
    βε
    0.06
     jung
    0.06
    äºŃ
    0.06
    ÂŃi
    0.06
    ROWSER
    0.06
    ÑĢÑĥÑĤ
    0.06
    564
    0.06
    Activations Density 0.042%

    No Known Activations