© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 89548
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the background and characteristics of musical artists

    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
    bes
    -0.07
    alth
    -0.07
    Bes
    -0.07
     similarly
    -0.06
    ucs
    -0.06
    emes
    -0.06
    ula
    -0.06
    é¤
    -0.06
    çŃĭ
    -0.06
     Simply
    -0.06
    POSITIVE LOGITS
    åį´
    0.09
    lero
    0.08
    ven
    0.07
    phin
    0.07
    anner
    0.07
    tera
    0.07
    ÑģÑĸ
    0.06
    lide
    0.06
     Bras
    0.06
    igne
    0.06
    Activations Density 0.031%

    No Known Activations