© 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. 5510
    Prev
    Next
    INDEX
    Explanations

    elements related to safety and accessibility within residential contexts

    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
    ible
    -0.07
    ERT
    -0.06
    \Abstract
    -0.06
    351
    -0.06
    97
    -0.06
     flooring
    -0.06
    _floor
    -0.06
    οÏĤ
    -0.06
    rent
    -0.06
    859
    -0.06
    POSITIVE LOGITS
     neighbors
    0.16
     neighbours
    0.14
     neighbor
    0.14
     Neighbor
    0.13
     neighbour
    0.13
    neighbors
    0.13
    éĤ
    0.12
    Neighbors
    0.12
    Neighbor
    0.12
     neighborhood
    0.11
    Activations Density 0.070%

    No Known Activations