© 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. 62200
    Prev
    Next
    INDEX
    Explanations

    terms related to delegations and their roles

    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
    raq
    -0.08
    ses
    -0.08
    xes
    -0.07
    ello
    -0.07
    itan
    -0.07
    éli
    -0.07
    yal
    -0.07
    ledged
    -0.07
    rike
    -0.07
    sey
    -0.07
    POSITIVE LOGITS
    hips
    0.07
    hip
    0.07
    hift
    0.07
    ä¼į
    0.07
    FlowLayout
    0.07
    ettings
    0.07
    hdr
    0.07
    aux
    0.06
    china
    0.06
    wart
    0.06
    Activations Density 0.005%

    No Known Activations