© 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. 18087
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate offerings or opportunities for exploration and learning

    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
    гов
    -0.07
     redirection
    -0.07
    raphics
    -0.07
    OfYear
    -0.07
    ÑĢазÑĥ
    -0.07
    rikes
    -0.06
    çĻ»
    -0.06
    à¤ķरण
    -0.06
    stery
    -0.06
    /setup
    -0.06
    POSITIVE LOGITS
     code
    0.07
    enty
    0.06
     bloc
    0.06
     inheritance
    0.06
     меж
    0.06
    .compile
    0.06
     create
    0.06
     functions
    0.06
     Luo
    0.06
     Crate
    0.06
    Activations Density 0.000%

    No Known Activations