© 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. 15804
    Prev
    Next
    INDEX
    Explanations

    HTML and XML closing tags

    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
     Vys
    -0.07
    olumn
    -0.07
    spo
    -0.06
    fen
    -0.06
    ier
    -0.06
    scal
    -0.06
    ereg
    -0.06
    ÐIJÑĢÑħÑĸвовано
    -0.06
    vak
    -0.06
    ieg
    -0.06
    POSITIVE LOGITS
    s
    0.11
    ÙĦ
    0.08
    iw
    0.07
    ed
    0.07
    aft
    0.07
    _RTC
    0.07
    eru
    0.07
    sar
    0.06
    sav
    0.06
    Ùĩ
    0.06
    Activations Density 0.058%

    No Known Activations