© 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. 83502
    Prev
    Next
    INDEX
    Explanations

    terms related to geography

    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
    æĭĽ
    -0.08
    /*č↵
    -0.07
    Ä°S
    -0.07
    纪
    -0.07
    ãĥĸãĥ©
    -0.06
    รà¸ģ
    -0.06
    eman
    -0.06
    imd
    -0.06
    lien
    -0.06
    ogo
    -0.06
    POSITIVE LOGITS
    å¹¹ç·ļ
    0.08
    orget
    0.07
     quotient
    0.07
    961
    0.07
     miêu
    0.06
    ffe
    0.06
    IRMWARE
    0.06
    features
    0.06
    hta
    0.06
    herits
    0.06
    Activations Density 0.002%

    No Known Activations