© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 80837
    Prev
    Next
    INDEX
    Explanations

    references to notable musical transitions and developments

    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
    leo
    -0.07
    lue
    -0.07
    asco
    -0.07
    rchive
    -0.07
     Mime
    -0.07
    hek
    -0.07
    gne
    -0.07
    leigh
    -0.07
    enko
    -0.07
     ActionTypes
    -0.06
    POSITIVE LOGITS
    ê³Ħ
    0.07
     ÑģлÑĥ
    0.06
    æ´Ĺ
    0.06
    sz
    0.06
     artists
    0.06
    onica
    0.06
    WithIdentifier
    0.06
    æĴ
    0.06
     bands
    0.05
    ilos
    0.05
    Activations Density 0.023%

    No Known Activations