© 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. 105114
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational structure and appointments

    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
    екаÑĢ
    -0.07
    porter
    -0.07
    haft
    -0.07
    fak
    -0.07
    iples
    -0.06
    ãĢģç§ģ
    -0.06
    MethodImpl
    -0.06
    .Encode
    -0.06
     Rap
    -0.06
    rap
    -0.06
    POSITIVE LOGITS
     appointment
    0.12
     appointments
    0.12
     Appointment
    0.11
     appoint
    0.10
    Appointment
    0.10
    appoint
    0.09
    appointment
    0.09
     назнаÑĩ
    0.09
     positions
    0.08
     appointed
    0.07
    Activations Density 0.015%

    No Known Activations