© 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. 16360
    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
    รà¸ģ
    -0.08
    /browse
    -0.08
    amac
    -0.08
    zcze
    -0.08
    ascript
    -0.07
    jišť
    -0.07
    ä¸Ī
    -0.07
    ivec
    -0.07
    _ABC
    -0.07
     WARRANT
    -0.07
    POSITIVE LOGITS
    's
    0.07
    ~
    0.06
    ough
    0.06
    enen
    0.05
    base
    0.05
    kate
    0.05
    ervers
    0.05
    _
    0.05
    dej
    0.05
    __
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.