© 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 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. 71348
    Prev
    Next
    INDEX
    Explanations

    expressions of personal desire and emotional connection

    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
    rank
    -0.07
    agma
    -0.07
    urv
    -0.06
    lectual
    -0.06
    کت
    -0.06
     bana
    -0.06
    _STORAGE
    -0.06
    ÑĢив
    -0.06
    rica
    -0.06
    woff
    -0.06
    POSITIVE LOGITS
     wanted
    0.09
    wanted
    0.07
    enheim
    0.07
    iles
    0.06
    enso
    0.06
    ãĤŃãĥ¥
    0.06
     setLocation
    0.06
     felt
    0.06
    arda
    0.06
    iban
    0.06
    Activations Density 0.049%

    No Known Activations