© 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. 15483
    Prev
    Next
    INDEX
    Explanations

    information related to legal and administrative processes for marriage registration

    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
    upp
    -0.08
    inea
    -0.06
    dyn
    -0.06
    öh
    -0.06
    me
    -0.06
    è¼ī
    -0.06
    íĺ¸
    -0.06
    udos
    -0.06
    ily
    -0.05
    udd
    -0.05
    POSITIVE LOGITS
     nearest
    0.10
    nearest
    0.09
     local
    0.07
     appropriate
    0.07
    closest
    0.07
    ç¿Ķ
    0.07
     closest
    0.07
     regional
    0.07
     territorial
    0.07
    (.)
    0.07
    Activations Density 0.024%

    No Known Activations