© 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. 5444
    Prev
    Next
    INDEX
    Explanations

    codes or identifiers, likely related to research articles or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    inel
    -0.08
    625
    -0.07
    arge
    -0.07
    ../../../
    -0.07
    ButtonType
    -0.07
    ocale
    -0.07
    asto
    -0.06
    оÑĩной
    -0.06
    VG
    -0.06
    astos
    -0.06
    POSITIVE LOGITS
    nd
    0.11
    ND
    0.08
    ucha
    0.07
    .lib
    0.07
    chl
    0.07
    MAC
    0.06
    мм
    0.06
    ship
    0.06
    cha
    0.06
    ndata
    0.06
    Activations Density 0.027%

    No Known Activations