© 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. 17-LLAMASCOPE-RES-131K
    11. 106411
    Prev
    Next
    INDEX
    Explanations

    programming-related functions and operations

    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
     homo
    -0.06
     Lat
    -0.06
    izi
    -0.06
    bl
    -0.06
    irs
    -0.06
     kho
    -0.06
    ko
    -0.06
    ance
    -0.06
     ko
    -0.06
     Gir
    -0.06
    POSITIVE LOGITS
    ugo
    0.08
    FromString
    0.08
    uddy
    0.08
    $MESS
    0.08
     !***
    0.08
    .datab
    0.07
    mav
    0.07
    ieg
    0.07
     stringWith
    0.07
    ISTR
    0.07
    Activations Density 0.020%

    No Known Activations