© 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. 30990
    Prev
    Next
    INDEX
    Explanations

    trends and statistics related to crime and violence

    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
    itational
    -0.07
    mae
    -0.07
    esk
    -0.07
    _topology
    -0.06
    utsch
    -0.06
    ournal
    -0.06
    rimp
    -0.06
    ellar
    -0.06
    zsche
    -0.06
    esine
    -0.06
    POSITIVE LOGITS
     lately
    0.10
     recent
    0.09
     recently
    0.08
     since
    0.08
    recent
    0.07
    since
    0.07
    Recently
    0.07
    æľĢè¿ij
    0.06
    669
    0.06
     partly
    0.06
    Activations Density 0.026%

    No Known Activations