© 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. 4648
    Prev
    Next
    INDEX
    Explanations

    references to programming functions and plugins

    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
    acci
    -0.06
    lisi
    -0.06
    zilla
    -0.06
    idon
    -0.06
    issy
    -0.06
    že
    -0.06
    éĽ
    -0.06
    Ưá»
    -0.06
    uve
    -0.06
    iesen
    -0.06
    POSITIVE LOGITS
    ç®±
    0.07
    éIJĺ
    0.06
    REFERRED
    0.06
    cela
    0.06
    ë£Į
    0.06
    .this
    0.06
    oti
    0.06
    inic
    0.06
    .::
    0.06
     Associ
    0.06
    Activations Density 0.040%

    No Known Activations