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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26973
    Prev
    Next
    INDEX
    Explanations

    references to voting and elections

    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
    ilib
    -0.07
    umin
    -0.07
    uez
    -0.07
     serialVersionUID
    -0.06
    ooter
    -0.06
    nbsp
    -0.06
    arrants
    -0.06
    ATAL
    -0.06
    zend
    -0.06
    azers
    -0.06
    POSITIVE LOGITS
    .Dot
    0.07
    nul
    0.07
    .tom
    0.07
    /MIT
    0.07
    .Formatting
    0.06
    vip
    0.06
    visa
    0.06
    \Doctrine
    0.06
     František
    0.06
     FLAG
    0.06
    Activations Density 0.000%

    No Known Activations