© 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. 79615
    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
     nues
    -0.06
    [^
    -0.06
    irs
    -0.06
    -0.06
    -0.06
    é¦Ļ
    -0.06
     denom
    -0.06
    oya
    -0.06
     poil
    -0.05
     peri
    -0.05
    POSITIVE LOGITS
    orsk
    0.08
    ocator
    0.07
    kke
    0.07
    chsel
    0.07
    uling
    0.07
    resse
    0.07
    olian
    0.07
    inea
    0.07
    ENSE
    0.07
    lÃŃn
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.