© 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. 9-LLAMASCOPE-RES-131K
    11. 97794
    Prev
    Next
    INDEX
    Explanations

    names of organizations and institutions, particularly those related to community or health services

    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
    spo
    -0.07
    ucken
    -0.07
    iley
    -0.06
    fu
    -0.06
    igo
    -0.06
    iene
    -0.06
    åĢĴ
    -0.06
    ingo
    -0.06
    SR
    -0.06
    ff
    -0.05
    POSITIVE LOGITS
    ovky
    0.08
    éĥ
    0.07
    rawn
    0.07
    teÅŁ
    0.07
    ùa
    0.07
    ÏĦεÏģο
    0.07
    ÏĦεÏģ
    0.07
    .mixin
    0.07
    eza
    0.07
    è¨
    0.07
    Activations Density 0.020%

    No Known Activations