© 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. 14935
    Prev
    Next
    INDEX
    Explanations

    elements related to API components and resources in a programming context

    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
    preneur
    -0.06
    rame
    -0.06
    és
    -0.06
    otton
    -0.05
    es
    -0.05
    950
    -0.05
     Holy
    -0.05
    aille
    -0.05
    rale
    -0.05
    Âł
    -0.05
    POSITIVE LOGITS
    Ĺı
    0.07
    .Generated
    0.07
    ÑĮко
    0.07
    .='
    0.07
    ŀĭ
    0.07
    íĭ
    0.07
    slaught
    0.07
     OSD
    0.07
    ÑĥÑĩ
    0.06
    hlen
    0.06
    Activations Density 0.001%

    No Known Activations