© 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. 29930
    Prev
    Next
    INDEX
    Explanations

    references to an audience or audience-related concepts

    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
    ï¸ı
    -0.09
    ordes
    -0.08
    ovel
    -0.08
    enda
    -0.07
    ÑĨиÑĤ
    -0.07
    öst
    -0.07
    ching
    -0.07
    utow
    -0.07
    bow
    -0.07
    ichick
    -0.07
    POSITIVE LOGITS
    hip
    0.08
     members
    0.07
    /view
    0.06
     member
    0.06
     Ear
    0.06
    visa
    0.06
    /client
    0.06
    oucher
    0.06
     demand
    0.06
    важа
    0.06
    Activations Density 0.009%

    No Known Activations