© 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. 97997
    Prev
    Next
    INDEX
    Explanations

    names and titles associated with music or songs

    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
    engin
    -0.09
    ANJI
    -0.08
    ẻ
    -0.08
    tiler
    -0.07
    izzo
    -0.07
    onne
    -0.07
     iddi
    -0.07
    ossa
    -0.07
    ussy
    -0.07
    ÑĦик
    -0.07
    POSITIVE LOGITS
    "url
    0.06
    258
    0.06
     tri
    0.06
    amoto
    0.06
    ippers
    0.05
     Tru
    0.05
    .complete
    0.05
    imedia
    0.05
     liv
    0.05
    ahr
    0.05
    Activations Density 0.003%

    No Known Activations