© 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. 88574
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocacy and support for health and human rights organizations

    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
    jur
    -0.08
    iph
    -0.08
    mue
    -0.07
    unya
    -0.07
    à¹Ģศ
    -0.07
    hipster
    -0.07
    kte
    -0.07
    iper
    -0.07
     culpa
    -0.07
    alion
    -0.07
    POSITIVE LOGITS
     whom
    0.07
     ref
    0.06
     balance
    0.06
     justice
    0.06
    IJ
    0.06
     Justice
    0.06
    /vendors
    0.06
     Tod
    0.06
    114
    0.06
    ensible
    0.06
    Activations Density 0.007%

    No Known Activations