© 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. 55153
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to responsibility and guidelines associated with actions or behaviors

    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
    @nate
    -0.08
     Sphinx
    -0.07
    /*č↵
    -0.07
    ouden
    -0.07
    tright
    -0.07
    chio
    -0.07
    aight
    -0.07
    ä¸Ķ
    -0.07
    haf
    -0.07
     Meaning
    -0.07
    POSITIVE LOGITS
    inas
    0.08
     always
    0.07
    ODE
    0.07
     first
    0.06
     besides
    0.06
     siempre
    0.06
     ALWAYS
    0.06
    always
    0.06
    Ed
    0.06
     Edmund
    0.06
    Activations Density 0.035%

    No Known Activations