© 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 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. 17-LLAMASCOPE-RES-131K
    11. 60963
    Prev
    Next
    INDEX
    Explanations

    user interface components related to buttons and navigation elements

    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
    -0.07
    209
    -0.06
     odd
    -0.06
    ugh
    -0.06
    uc
    -0.06
    омеÑĢ
    -0.06
    ux
    -0.06
    oh
    -0.06
    945
    -0.06
    odi
    -0.05
    POSITIVE LOGITS
    voie
    0.08
    -primary
    0.07
    actionDate
    0.07
    _##
    0.07
    $MESS
    0.07
    acades
    0.07
    pell
    0.07
    icari
    0.07
    ÎĪ
    0.07
    ãĥĨãĥ«
    0.07
    Activations Density 0.002%

    No Known Activations