© 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. 14596
    Prev
    Next
    INDEX
    Explanations

    elements related to sharing or distributing information and content

    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
    sonian
    -0.06
    olla
    -0.06
    eme
    -0.06
    awan
    -0.06
    enne
    -0.06
     Stall
    -0.06
     ut
    -0.06
     ÑĢеÑģ
    -0.06
    olas
    -0.06
    prit
    -0.06
    POSITIVE LOGITS
    elon
    0.07
     recipient
    0.07
    ÄĽÅ¾
    0.07
    éĤ
    0.07
     Mand
    0.07
    zcze
    0.07
     initWithNibName
    0.06
    emez
    0.06
    تÙĩا
    0.06
    åªĴ
    0.06
    Activations Density 0.002%

    No Known Activations