© 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. 9-LLAMASCOPE-RES-131K
    11. 98285
    Prev
    Next
    INDEX
    Explanations

    references to updates or changes in news articles

    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
    aly
    -0.07
    ussen
    -0.06
    cec
    -0.06
    king
    -0.06
    io
    -0.06
    alen
    -0.06
    vin
    -0.06
    ced
    -0.06
     Resume
    -0.06
    is
    -0.06
    POSITIVE LOGITS
    DOG
    0.08
     MacDonald
    0.07
    owell
    0.07
     hrom
    0.07
     eius
    0.07
    pcf
    0.07
    ij
    0.07
    amac
    0.07
    ARGIN
    0.07
    -uppercase
    0.07
    Activations Density 0.001%

    No Known Activations