© 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. 15-LLAMASCOPE-RES-131K
    11. 103939
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and associated terms

    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
    ipar
    -0.07
    kop
    -0.07
    à¥įवप
    -0.06
    wall
    -0.06
    _ANY
    -0.06
    ´Ī
    -0.06
     vhod
    -0.06
    ui
    -0.06
     coraz
    -0.06
    _utilities
    -0.06
    POSITIVE LOGITS
    SenderId
    0.06
    ↵
    0.06
     Tender
    0.06
    ëĿ¼ëĬĶ
    0.06
    .net
    0.06
    âĢ¦↵↵↵
    0.06
     Barg
    0.06
    ahu
    0.06
     ayrıca
    0.06
    adolu
    0.06
    Activations Density 0.004%

    No Known Activations