© 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. 14737
    Prev
    Next
    INDEX
    Explanations

    statistical and demographic information about households and families

    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
    instr
    -0.07
    isia
    -0.07
    nof
    -0.07
    panion
    -0.07
    iliar
    -0.07
    iever
    -0.06
    egen
    -0.06
    agen
    -0.06
     Comp
    -0.06
    ahoma
    -0.06
    POSITIVE LOGITS
    oric
    0.06
    mes
    0.06
    hani
    0.05
     Aless
    0.05
    ZA
    0.05
    shaw
    0.05
     indem
    0.05
     Nico
    0.05
    urovision
    0.05
    ÃŃ
    0.05
    Activations Density 0.001%

    No Known Activations