© 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 EvalsExportsAPI 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. 78496
    Prev
    Next
    INDEX
    Explanations

    HTML meta tags and their attributes

    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
     Pie
    -0.06
     online
    -0.06
    enal
    -0.05
     Cour
    -0.05
    -w
    -0.05
     Ups
    -0.05
     Fut
    -0.05
     sort
    -0.05
     e
    -0.05
     Agenda
    -0.05
    POSITIVE LOGITS
    .DataBindings
    0.08
    ÑģÑİ
    0.07
     maduras
    0.07
    λικ
    0.07
    _Static
    0.07
    ìĶ¨
    0.07
    .appspot
    0.07
     Mặt
    0.07
    .openg
    0.07
    UpInside
    0.07
    Activations Density 0.000%

    No Known Activations