© 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. 4926
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of life experiences and personal narratives

    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
    ESC
    -0.07
    Ãło
    -0.07
    tp
    -0.07
    uben
    -0.07
     Imm
    -0.07
     Loose
    -0.07
    ouz
    -0.07
    perse
    -0.06
    ÑĤоÑİ
    -0.06
    immel
    -0.06
    POSITIVE LOGITS
     life
    0.08
     adulthood
    0.07
     childhood
    0.07
    anmar
    0.07
     GUIDE
    0.07
    以æĿ¥
    0.07
    842
    0.07
    life
    0.07
     own
    0.06
    _life
    0.06
    Activations Density 0.004%

    No Known Activations