© 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. 17-LLAMASCOPE-RES-131K
    11. 93547
    Prev
    Next
    INDEX
    Explanations

    locations and contexts related to residential and commercial properties, particularly in relation to waste disposal and electrical setups

    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
    deaux
    -0.07
    hra
    -0.07
    etta
    -0.07
    izza
    -0.07
    olik
    -0.07
    éné
    -0.06
    ertil
    -0.06
    adh
    -0.06
     Barnes
    -0.06
    eder
    -0.06
    POSITIVE LOGITS
    lez
    0.07
    709
    0.06
     vest
    0.06
    ê´Ģ
    0.06
    TRS
    0.06
    FER
    0.06
    ãģ£ãģ¡
    0.06
    ju
    0.06
    -runtime
    0.06
    adden
    0.06
    Activations Density 0.017%

    No Known Activations