© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 69342
    Prev
    Next
    INDEX
    Explanations

    terms related to non-standard physical theories

    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
    æĭ³
    -0.07
    jee
    -0.07
    rente
    -0.07
    Ь
    -0.07
    gere
    -0.07
    bine
    -0.06
    oor
    -0.06
    !=(
    -0.06
    lock
    -0.06
    GLOBALS
    -0.06
    POSITIVE LOGITS
     ideal
    0.08
    oko
    0.06
    reau
    0.06
     trivial
    0.06
    _Api
    0.06
    ancement
    0.06
    erval
    0.06
    eur
    0.06
    iz
    0.06
    ocre
    0.06
    Activations Density 0.025%

    No Known Activations