© 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. 9-LLAMASCOPE-RES-131K
    11. 95349
    Prev
    Next
    INDEX
    Explanations

    geographical locations and descriptions of places

    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
    andy
    -0.06
    utton
    -0.06
    pei
    -0.06
     Schmidt
    -0.06
    setItem
    -0.06
     ply
    -0.06
    osterone
    -0.06
    olik
    -0.06
    ousel
    -0.05
    omon
    -0.05
    POSITIVE LOGITS
     lá»Ļ
    0.07
     otherwise
    0.06
     HEAP
    0.06
    æk
    0.06
     modelName
    0.06
    IMER
    0.06
    _capabilities
    0.06
     Discipline
    0.06
    orf
    0.06
    жи
    0.06
    Activations Density 0.029%

    No Known Activations