© 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. 86503
    Prev
    Next
    INDEX
    Explanations

    expressions of personal emotion and advocacy

    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
    asaki
    -0.07
    swick
    -0.07
    .epoch
    -0.07
     addCriterion
    -0.07
    onso
    -0.07
    UNDLE
    -0.07
    ÑĮогоднÑĸ
    -0.07
    ÅĻe
    -0.07
    جب
    -0.07
     Ulus
    -0.07
    POSITIVE LOGITS
     Vance
    0.06
    avian
    0.06
     Morg
    0.06
     plains
    0.06
    andid
    0.06
    yla
    0.06
     Silk
    0.05
     Carb
    0.05
    aby
    0.05
    NY
    0.05
    Activations Density 0.005%

    No Known Activations