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. 96162
    Prev
    Next
    INDEX
    Explanations

    expressions of confusion or requests for help regarding coding issues

    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
     Boeh
    -0.07
     Angiospermae
    -0.06
    -caret
    -0.06
     cust
    -0.06
     Cousins
    -0.06
    orden
    -0.06
     dep
    -0.06
     Mills
    -0.06
    806
    -0.06
    izo
    -0.06
    POSITIVE LOGITS
    à¥Ĥस
    0.07
    ÑģÑĤÑĭ
    0.07
    spath
    0.06
    بÛĮÙĨÛĮ
    0.06
     geil
    0.06
    idle
    0.06
    DSL
    0.06
     Superman
    0.06
    ä¿Ĥ
    0.06
    acher
    0.06
    Activations Density 0.050%

    No Known Activations