© 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. 16494
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     councill
    -0.07
    GRAM
    -0.07
    erializer
    -0.07
    елÑĮ
    -0.06
     Auch
    -0.06
    eker
    -0.06
    .bit
    -0.06
     ape
    -0.06
    anel
    -0.06
    idenav
    -0.06
    POSITIVE LOGITS
    á»Ļt
    0.07
    except
    0.06
    åĨµ
    0.06
    hiba
    0.06
    dub
    0.06
    dej
    0.06
    chair
    0.06
    (Photo
    0.06
    lez
    0.06
    nown
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.