© 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. 72283
    Prev
    Next
    INDEX
    Explanations

    features and elements of residential properties

    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
    ´Ŀ
    -0.07
    gne
    -0.07
    @student
    -0.07
    óm
    -0.07
     пÑĥÑĤем
    -0.07
    Ỽt
    -0.07
    jadi
    -0.07
    lut
    -0.07
    peg
    -0.06
    ê»
    -0.06
    POSITIVE LOGITS
     imported
    0.06
     Front
    0.06
     throughout
    0.06
    usters
    0.06
     Dame
    0.06
     Leer
    0.06
     everywhere
    0.06
    art
    0.06
     Dim
    0.06
     Cummings
    0.05
    Activations Density 0.015%

    No Known Activations