© 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. 94972
    Prev
    Next
    INDEX
    Explanations

    instances of conditional logic and references to state management in programming

    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
     Roman
    -0.07
    Peer
    -0.06
    PE
    -0.06
    pon
    -0.06
    .componentInstance
    -0.06
    ãĥ³ãĥĨ
    -0.06
    iler
    -0.06
    Needs
    -0.06
    inger
    -0.06
     PE
    -0.06
    POSITIVE LOGITS
     éĬ
    0.08
    ábado
    0.08
    DED
    0.07
     avoids
    0.07
     properly
    0.07
    SED
    0.07
    otte
    0.07
    eba
    0.07
    à¸Īะà¹Ħà¸Ķ
    0.07
    chas
    0.07
    Activations Density 0.063%

    No Known Activations