© 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. 17-LLAMASCOPE-RES-131K
    11. 17077
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical and historical descriptions

    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
    oric
    -0.07
    AINER
    -0.07
    fy
    -0.07
    ainer
    -0.06
    loub
    -0.06
    ï¼ĭ
    -0.06
    รà¸ģ
    -0.06
    isation
    -0.06
    ména
    -0.06
    uga
    -0.06
    POSITIVE LOGITS
    216
    0.07
    416
    0.07
    psc
    0.06
     Pap
    0.06
    .Lang
    0.06
    anager
    0.06
    ymous
    0.06
    (er
    0.06
     Misc
    0.06
    .asp
    0.06
    Activations Density 0.015%

    No Known Activations