© 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. 78445
    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
    ertiary
    -0.06
    errar
    -0.06
    riere
    -0.06
    indrical
    -0.06
     ðŁĺī↵↵
    -0.06
     somewhat
    -0.06
    gran
    -0.06
     Gran
    -0.06
    .community
    -0.06
    ocale
    -0.06
    POSITIVE LOGITS
    ADX
    0.07
    ắt
    0.07
     misunder
    0.06
    HIR
    0.06
    _TM
    0.06
     ấm
    0.06
    472
    0.06
     nobody
    0.06
    undra
    0.06
    STD
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.