© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77943
    Prev
    Next
    INDEX
    Explanations

    action-oriented commands or instructions

    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
    ause
    -0.08
    emin
    -0.07
    htub
    -0.07
    tas
    -0.07
    immel
    -0.07
     Emer
    -0.07
     Ade
    -0.07
     cust
    -0.06
    owie
    -0.06
    indows
    -0.06
    POSITIVE LOGITS
     lev
    0.06
     BDS
    0.06
    .Guna
    0.06
    alia
    0.06
     pha
    0.06
    subtype
    0.06
     AXIS
    0.06
    heim
    0.06
    ;!
    0.06
     quán
    0.06
    Activations Density 0.016%

    No Known Activations