© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 16031
    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
    aeper
    -0.09
    ango
    -0.08
    ANGO
    -0.07
    trak
    -0.07
    .Orientation
    -0.07
     <!--[
    -0.07
    инки
    -0.07
    hem
    -0.07
    ÑĢап
    -0.07
    ozor
    -0.07
    POSITIVE LOGITS
    ilis
    0.06
    ader
    0.05
    OT
    0.05
    _zeros
    0.05
    len
    0.05
    ly
    0.05
    éĺħ
    0.05
    ots
    0.05
    ar
    0.05
     outlines
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.