© 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. 9-LLAMASCOPE-RES-131K
    11. 98911
    Prev
    Next
    INDEX
    Explanations

    references to magic or magical 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
    ãģŁãĤī
    -0.08
    astr
    -0.07
    層
    -0.07
    icken
    -0.06
    ointment
    -0.06
    lá
    -0.06
    etto
    -0.06
    eto
    -0.06
    /preferences
    -0.06
    inue
    -0.06
    POSITIVE LOGITS
    alex
    0.06
    »
    0.06
    BackgroundColor
    0.06
    -human
    0.06
     Colon
    0.06
    odus
    0.06
     Hardware
    0.06
     ile
    0.05
     svens
    0.05
     noble
    0.05
    Activations Density 0.005%

    No Known Activations