© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26742
    Prev
    Next
    INDEX
    Explanations

    key concepts related to fundamental principles and rights

    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
    uw
    -0.07
    scape
    -0.07
    agen
    -0.07
    sdale
    -0.06
    ãĥĨãĥ«
    -0.06
    Ìĥ
    -0.06
     Spectrum
    -0.06
    offs
    -0.06
    bit
    -0.06
    abilit
    -0.06
    POSITIVE LOGITS
    mente
    0.14
    ity
    0.09
    most
    0.09
    /basic
    0.08
    /original
    0.08
    lest
    0.08
    emente
    0.08
    ist
    0.08
    arily
    0.07
    istically
    0.07
    Activations Density 0.010%

    No Known Activations