© 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. 88919
    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
    rtc
    -0.07
     bol
    -0.07
    /query
    -0.06
    ropoda
    -0.06
    ertility
    -0.06
    ensburg
    -0.06
    uyen
    -0.06
    ertest
    -0.06
    gewater
    -0.06
    eton
    -0.06
    POSITIVE LOGITS
    pek
    0.06
    zet
    0.06
    ponents
    0.06
    ालà¤ķ
    0.06
    esModule
    0.06
    chal
    0.06
    alu
    0.06
    mpz
    0.06
    ellers
    0.06
    suppress
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.