© 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. 73935
    Prev
    Next
    INDEX
    Explanations

    phrases related to home electrical wiring and switch installation

    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
    inh
    -0.06
    eca
    -0.06
    ivy
    -0.06
    ket
    -0.06
    vais
    -0.06
    ivr
    -0.06
    crm
    -0.06
     èŤ
    -0.06
    ims
    -0.06
    ahy
    -0.06
    POSITIVE LOGITS
    .shell
    0.07
     congr
    0.07
    ocs
    0.07
    AtPath
    0.06
    riad
    0.06
    éŃ
    0.06
    лада
    0.06
    éģĩ
    0.06
    à¥Įà¤Ĥ
    0.06
    .swt
    0.06
    Activations Density 0.001%

    No Known Activations