© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29603
    Prev
    Next
    INDEX
    Explanations

    geographical boundaries and locations

    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
    ANDOM
    -0.07
    ien
    -0.07
    tero
    -0.06
     Campos
    -0.06
     Buccane
    -0.06
    ARA
    -0.06
    arendra
    -0.06
    èIJ½ãģ¡
    -0.06
    Bloc
    -0.06
    inka
    -0.06
    POSITIVE LOGITS
     border
    0.07
    rait
    0.07
     boundary
    0.07
     premium
    0.06
    imest
    0.06
    fol
    0.06
     borders
    0.06
     Demir
    0.06
    724
    0.06
     neighbors
    0.06
    Activations Density 0.003%

    No Known Activations