© 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. 73119
    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
    kla
    -0.06
    deen
    -0.06
    itr
    -0.06
    aru
    -0.06
     geek
    -0.06
     ...
    -0.05
     basic
    -0.05
     permanently
    -0.05
    ç§
    -0.05
     Geek
    -0.05
    POSITIVE LOGITS
     Goals
    0.09
     goals
    0.08
    FileSync
    0.07
     Goal
    0.07
    agna
    0.07
     goal
    0.07
    -goal
    0.07
    SMART
    0.07
    FAILURE
    0.07
    Goal
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.