© 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. 17-LLAMASCOPE-RES-131K
    11. 59603
    Prev
    Next
    INDEX
    Explanations

    numerical and statistical data points

    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
    oen
    -0.07
    aes
    -0.07
    olley
    -0.07
    Ñĥва
    -0.06
    ainer
    -0.06
    اÙĪÙĦ
    -0.06
    kowski
    -0.06
    ossier
    -0.06
    itta
    -0.06
    enz
    -0.06
    POSITIVE LOGITS
    vyk
    0.07
    zilla
    0.07
    _suspend
    0.06
    ÂłkW
    0.06
    RIES
    0.06
     Haram
    0.06
    OffsetTable
    0.06
     domic
    0.06
    âĢª
    0.06
    'icon
    0.06
    Activations Density 0.035%

    No Known Activations