© 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. 5557
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate roles or titles within organizational structures

    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
     private
    -0.08
     alone
    -0.07
    _private
    -0.07
     mother
    -0.07
    253
    -0.07
    private
    -0.07
     aside
    -0.07
    /private
    -0.06
    Solo
    -0.06
    Mother
    -0.06
    POSITIVE LOGITS
    ERGE
    0.06
    adem
    0.06
    acz
    0.06
    onte
    0.06
    ertas
    0.06
    shint
    0.06
    layouts
    0.06
    /epl
    0.06
    opsis
    0.06
    _compat
    0.06
    Activations Density 0.004%

    No Known Activations