© 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. 117276
    Prev
    Next
    INDEX
    Explanations

    names of characters and actors from film and television

    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
    rowse
    -0.09
     DependencyProperty
    -0.08
    prite
    -0.07
    ampaign
    -0.07
    ijke
    -0.07
    _apps
    -0.07
    ioc
    -0.07
     mastur
    -0.07
    Displayed
    -0.07
    ohon
    -0.06
    POSITIVE LOGITS
     etc
    0.07
     Maxim
    0.07
     others
    0.06
    Ranges
    0.06
     Cord
    0.06
     cant
    0.06
     Others
    0.06
    ova
    0.06
    OPTION
    0.06
     Dialogue
    0.06
    Activations Density 0.005%

    No Known Activations