© 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. 3619
    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
    olik
    -0.08
    illet
    -0.07
    ermo
    -0.07
    éĮ
    -0.07
    ackbar
    -0.07
     numberOfRows
    -0.07
    jez
    -0.06
    altung
    -0.06
    fsp
    -0.06
    formatter
    -0.06
    POSITIVE LOGITS
    ng
    0.07
    noinspection
    0.06
    lee
    0.06
    iton
    0.06
    ur
    0.06
    ležit
    0.06
     calor
    0.06
     canv
    0.06
     SOS
    0.06
     Ferr
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.