© 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. 9-LLAMASCOPE-RES-131K
    11. 97849
    Prev
    Next
    INDEX
    Explanations

    brand names or designers' names

    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
    ipple
    -0.06
    ief
    -0.06
    olg
    -0.06
     Gol
    -0.06
    iem
    -0.06
     Todd
    -0.06
    als
    -0.06
    geh
    -0.06
    rous
    -0.06
    udo
    -0.06
    POSITIVE LOGITS
    ITA
    0.07
    wner
    0.07
    PostBack
    0.07
    DIM
    0.07
    .createFrom
    0.07
    reon
    0.07
    ioneer
    0.07
     ЧаÑģ
    0.07
    braco
    0.07
    aines
    0.07
    Activations Density 0.009%

    No Known Activations