© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 96798
    Prev
    Next
    INDEX
    Explanations

    geographical locations and their associations

    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
    annies
    -0.07
    ety
    -0.07
    ãĥ¥ãĥ¼
    -0.07
     Erotische
    -0.07
    .UnitTesting
    -0.06
    ima
    -0.06
    apters
    -0.06
    uner
    -0.06
    ippo
    -0.06
    ãĥ§
    -0.06
    POSITIVE LOGITS
    olland
    0.07
    ãģ²
    0.06
     Eag
    0.06
    اÛĮÛĮ
    0.06
    ëĵľë¦¬
    0.06
    Ñħи
    0.06
    -wide
    0.06
     Canter
    0.06
    KeyValue
    0.06
     overall
    0.06
    Activations Density 0.054%

    No Known Activations