© 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. 18210
    Prev
    Next
    INDEX
    Explanations

    references to view counts and details in a promotional or informational context

    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
    enga
    -0.07
    óng
    -0.07
    .Reporting
    -0.07
    olon
    -0.07
    _compat
    -0.07
    лаз
    -0.06
    æİĽ
    -0.06
    oldem
    -0.06
    ÑĪев
    -0.06
    iminal
    -0.06
    POSITIVE LOGITS
    DU
    0.07
    ìĽħ
    0.05
    èĢ
    0.05
    zos
    0.05
    unden
    0.05
    Premium
    0.05
    Opp
    0.05
    ">//
    0.05
    à¸Ķร
    0.05
     meas
    0.05
    Activations Density 0.001%

    No Known Activations