© 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. 119205
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "born" and related expressions of birth

    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
    annon
    -0.07
    нÑĮ
    -0.06
    ÑĥÑĢÑģ
    -0.06
    uler
    -0.06
    jerne
    -0.06
    ibe
    -0.06
    vore
    -0.06
    onal
    -0.06
    iem
    -0.06
     zar
    -0.06
    POSITIVE LOGITS
    IALOG
    0.06
    apı
    0.06
    HORT
    0.06
    شتÙĩ
    0.06
    LOAT
    0.06
    ÅĻej
    0.06
     dabei
    0.06
    èģ½
    0.06
    nu
    0.06
     sıras
    0.06
    Activations Density 0.002%

    No Known Activations