Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96169
    Prev
    Next
    INDEX
    Explanations

    descriptions related to outdoor activities and natural landscapes

    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
    quan
    -0.07
    ãĤ¿ãĥ³
    -0.07
    atas
    -0.07
    437
    -0.07
     ÑģÑħод
    -0.06
     ++)↵
    -0.06
    radient
    -0.06
    .btnClose
    -0.06
    vre
    -0.06
    inces
    -0.06
    POSITIVE LOGITS
     Associ
    0.07
     Morph
    0.06
    umatic
    0.06
    .require
    0.05
    mland
    0.05
     pul
    0.05
    esti
    0.05
     Divine
    0.05
     flow
    0.05
     sc
    0.05
    Activations Density 0.003%

    No Known Activations