© 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. 17-LLAMASCOPE-RES-131K
    11. 30255
    Prev
    Next
    INDEX
    Explanations

    instances of the word "cant" or its variations

    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
    iê
    -0.07
    bling
    -0.06
    ieg
    -0.06
     Sho
    -0.06
    thetic
    -0.06
    =explode
    -0.06
    uforia
    -0.06
    ViewControllerAnimated
    -0.06
    med
    -0.06
     IconData
    -0.06
    POSITIVE LOGITS
    anker
    0.09
     dov
    0.06
    .fm
    0.06
    UCKET
    0.06
     Cool
    0.06
    究
    0.06
    yaw
    0.06
    lations
    0.06
     Missile
    0.06
    mere
    0.06
    Activations Density 0.007%

    No Known Activations