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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 71430
    Prev
    Next
    INDEX
    Explanations

    references to philosophical or literary writings and teachings

    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
    pitch
    -0.06
    odnÃŃ
    -0.06
    scape
    -0.06
    .intellij
    -0.06
    sÃŃ
    -0.06
    à¸Ĺาà¸Ļ
    -0.06
    ãģĦãĤĭ
    -0.06
    arth
    -0.06
    roke
    -0.06
     interrupts
    -0.05
    POSITIVE LOGITS
    ings
    0.10
    INGS
    0.07
    ippet
    0.07
     Mig
    0.07
    iger
    0.07
     Nacht
    0.07
    /books
    0.07
    _legacy
    0.07
     tslint
    0.06
    ISTRIBUT
    0.06
    Activations Density 0.008%

    No Known Activations