© 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. 98448
    Prev
    Next
    INDEX
    Explanations

    phrases relating to specific customizations or tailored features

    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
    रण
    -0.07
     Hlav
    -0.07
    oni
    -0.07
    hape
    -0.06
    iph
    -0.06
    ;element
    -0.06
    ibold
    -0.06
    _expired
    -0.06
    lei
    -0.06
    iesel
    -0.06
    POSITIVE LOGITS
    Ĥæķ°
    0.07
    urtle
    0.06
    IDER
    0.06
    -for
    0.06
    ilk
    0.06
     serial
    0.06
     Fitz
    0.06
    738
    0.06
    åºľ
    0.06
    åľ°
    0.06
    Activations Density 0.010%

    No Known Activations