© 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. 92639
    Prev
    Next
    INDEX
    Explanations

    themes related to individuality and personal experiences

    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
    nul
    -0.07
    vers
    -0.07
    ikan
    -0.07
    alo
    -0.07
    stable
    -0.06
     Kern
    -0.06
     wherever
    -0.06
    ikon
    -0.06
    deb
    -0.06
    uforia
    -0.06
    POSITIVE LOGITS
     unique
    0.14
     Unique
    0.12
    unique
    0.11
    Unique
    0.11
     uniqueness
    0.11
     UNIQUE
    0.10
    (unique
    0.10
    _unique
    0.10
     situation
    0.10
     uniquely
    0.09
    Activations Density 0.009%

    No Known Activations