© 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. 17794
    Prev
    Next
    INDEX
    Explanations

    words related to birth or origin

    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
    baugh
    -0.07
    #
    -0.07
    uby
    -0.07
    á»ijng
    -0.07
     Záp
    -0.06
     Emb
    -0.06
    ẩu
    -0.06
    stan
    -0.06
     Tobias
    -0.06
    çĮ«
    -0.06
    POSITIVE LOGITS
    ORA
    0.07
    ettel
    0.06
    utterstock
    0.06
    teg
    0.06
    722
    0.06
    zym
    0.06
    vided
    0.06
    quared
    0.06
     ÙħÙĤدÙħ
    0.06
    oard
    0.06
    Activations Density 0.002%

    No Known Activations