© 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. 117679
    Prev
    Next
    INDEX
    Explanations

    comparative and statistical terms related to values and performance metrics

    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
    idar
    -0.07
    äºŃ
    -0.06
    inking
    -0.06
    wiÄħ
    -0.06
    िण
    -0.06
    &e
    -0.06
    aptor
    -0.06
    IDGE
    -0.06
    mts
    -0.06
    quot
    -0.06
    POSITIVE LOGITS
    contra
    0.07
    argv
    0.06
    outu
    0.06
    -gnu
    0.06
    ÏĦÏīν
    0.06
    _icons
    0.06
    orton
    0.06
    yles
    0.06
    ThanOrEqualTo
    0.06
    ThanOr
    0.06
    Activations Density 0.003%

    No Known Activations