© 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 EvalsExportsAPI 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. 71325
    Prev
    Next
    INDEX
    Explanations

    measurements related to height

    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
    usher
    -0.07
    .dtp
    -0.07
    ocre
    -0.07
    iete
    -0.07
    QUEUE
    -0.07
    idla
    -0.07
    NDER
    -0.07
    hdl
    -0.07
    SSION
    -0.07
    umar
    -0.07
    POSITIVE LOGITS
     глÑĥ
    0.06
    -C
    0.05
    eping
    0.05
     Chester
    0.05
     Sap
    0.05
    CAD
    0.05
    DirectoryName
    0.05
     Steven
    0.05
    ormsg
    0.05
     homosexuals
    0.05
    Activations Density 0.001%

    No Known Activations