© 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. 98597
    Prev
    Next
    INDEX
    Explanations

    attribute assignments in HTML tags

    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
    omics
    -0.07
    rane
    -0.07
    736
    -0.06
    бав
    -0.06
    igel
    -0.06
    ISR
    -0.06
     Guards
    -0.06
    rana
    -0.06
    isers
    -0.06
    atore
    -0.06
    POSITIVE LOGITS
    ridge
    0.07
    ENCH
    0.06
    kal
    0.06
    vsp
    0.06
    reeze
    0.06
     Emm
    0.06
    alias
    0.06
    à¸Ŀ
    0.06
     اÙĦجز
    0.06
    ²
    0.06
    Activations Density 0.001%

    No Known Activations