© 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. 92514
    Prev
    Next
    INDEX
    Explanations

    references to media publications and their frequencies in a text

    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
    âĢ¦↵
    -0.07
    ookies
    -0.06
    arty
    -0.06
    ookie
    -0.06
    aka
    -0.06
    criptor
    -0.06
     Duis
    -0.06
    ÑĥÑĢÑĥ
    -0.06
    ault
    -0.06
    Std
    -0.05
    POSITIVE LOGITS
    //{{
    0.08
    'gc
    0.07
    ebek
    0.07
    entions
    0.07
    _Il
    0.07
    .binding
    0.07
    empt
    0.07
    aklı
    0.07
    ipse
    0.07
    (Android
    0.07
    Activations Density 0.016%

    No Known Activations