© 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. 89189
    Prev
    Next
    INDEX
    Explanations

    programming-related comments and annotations

    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
    interopRequire
    -0.06
    zet
    -0.06
     Voor
    -0.06
     Jacobs
    -0.06
     curb
    -0.06
    izzer
    -0.06
     Merr
    -0.06
    woke
    -0.06
    ///<
    -0.05
    è
    -0.05
    POSITIVE LOGITS
    rien
    0.07
    oleon
    0.07
    xda
    0.07
    ç¿Ķ
    0.07
    _NS
    0.07
    ANCH
    0.07
    ë¡ł
    0.06
    542
    0.06
    ancias
    0.06
    sov
    0.06
    Activations Density 0.002%

    No Known Activations