© 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. 94628
    Prev
    Next
    INDEX
    Explanations

    elements of character development, particularly focusing on addiction and personal struggles

    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
    reau
    -0.08
    ---</
    -0.08
    auc
    -0.08
     hâl
    -0.08
    Ä°T
    -0.08
    ipe
    -0.07
    uien
    -0.07
    .ExecuteReader
    -0.07
    consts
    -0.07
    à¸ı
    -0.07
    POSITIVE LOGITS
    avn
    0.06
    Âł
    0.06
     perpetrated
    0.06
    TableModel
    0.05
    .theme
    0.05
    alled
    0.05
    ..↵
    0.05
     Ms
    0.05
     Publisher
    0.05
    .
    0.05
    Activations Density 0.035%

    No Known Activations