© 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. 74098
    Prev
    Next
    INDEX
    Explanations

    topics associated with aid and resource management for the poor

    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
    iber
    -0.07
    ypo
    -0.06
    odo
    -0.06
    aper
    -0.06
    uant
    -0.06
    iler
    -0.06
    ÅĤ
    -0.06
     од
    -0.06
     ~>
    -0.06
    owski
    -0.06
    POSITIVE LOGITS
     mastur
    0.07
    strup
    0.07
    createClass
    0.07
    iversit
    0.07
    marvin
    0.07
    .Mapping
    0.06
    STYLE
    0.06
    @js
    0.06
    rhs
    0.06
    779
    0.06
    Activations Density 0.000%

    No Known Activations