© 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. 4811
    Prev
    Next
    INDEX
    Explanations

    words related to nesting or home-related concepts

    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
    cono
    -0.09
    ÑģÑĤиÑĩ
    -0.08
    æ°§
    -0.08
    èŁ
    -0.07
    thon
    -0.07
    inea
    -0.07
    nea
    -0.07
    idget
    -0.07
    ób
    -0.07
    елÑĸ
    -0.07
    POSITIVE LOGITS
    ings
    0.07
    ingu
    0.07
    flix
    0.07
     nest
    0.06
    oya
    0.06
    ro
    0.06
    ing
    0.06
    andard
    0.06
    ea
    0.06
    lé
    0.06
    Activations Density 0.006%

    No Known Activations