© 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 EvalsExportsAPI 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. 71297
    Prev
    Next
    INDEX
    Explanations

    empty or whitespace-only sections in the text

    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
     aure
    -0.07
    @brief
    -0.06
    elts
    -0.06
    abile
    -0.06
    VOID
    -0.06
    ieten
    -0.06
     Implemented
    -0.06
    azu
    -0.06
    enerima
    -0.06
    (PHP
    -0.06
    POSITIVE LOGITS
    .GroupLayout
    0.07
    ote
    0.06
    chin
    0.06
     Gross
    0.06
     Vital
    0.06
    ãĥ³ãĥIJ
    0.06
    ikon
    0.06
    },{↵
    0.06
     automáticamente
    0.06
    ãĥĨãĥ«
    0.06
    Activations Density 0.000%

    No Known Activations