© 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 EvalsExportsAPI 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. 76537
    Prev
    Next
    INDEX
    Explanations

    numerical data and identifiers relevant to resolutions or legislative actions

    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
    vala
    -0.07
    atin
    -0.06
    èª
    -0.06
    Ãły
    -0.06
    994
    -0.06
    onium
    -0.06
    ergy
    -0.06
    rin
    -0.06
     './../
    -0.06
    dÃŃ
    -0.06
    POSITIVE LOGITS
    ìĩ
    0.06
    venir
    0.06
     diseñador
    0.06
    izmet
    0.06
    ichten
    0.06
     pornstar
    0.06
    ennent
    0.06
    ailles
    0.06
    uniacid
    0.06
    à¤Ķर
    0.06
    Activations Density 0.025%

    No Known Activations