© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94272
    Prev
    Next
    INDEX
    Explanations

    references to human relationships and interactions

    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
    contres
    -0.08
     nuest
    -0.07
    ibr
    -0.07
    braco
    -0.07
    ediator
    -0.07
    ngr
    -0.07
    ichel
    -0.07
    ubar
    -0.07
    alendar
    -0.06
    ør
    -0.06
    POSITIVE LOGITS
     tête
    0.07
    è«ĩ
    0.06
     visitors
    0.06
     servant
    0.06
     Visitors
    0.06
     servants
    0.06
    eric
    0.06
    AME
    0.06
    _inds
    0.06
     quot
    0.06
    Activations Density 0.022%

    No Known Activations