© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 71895
    Prev
    Next
    INDEX
    Explanations

    details related to home care services and meal delivery options

    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
    serrat
    -0.07
    sanitize
    -0.07
    enie
    -0.07
    illos
    -0.06
    ãĤ¸ãĤª
    -0.06
    sil
    -0.06
    izer
    -0.06
    ulum
    -0.06
    ufen
    -0.06
    ruz
    -0.06
    POSITIVE LOGITS
     home
    0.07
     careg
    0.07
     companions
    0.07
     homem
    0.07
     Tempo
    0.07
     Eld
    0.07
     Medicare
    0.07
     bols
    0.06
    home
    0.06
     hjem
    0.06
    Activations Density 0.002%

    No Known Activations