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. 95946
    Prev
    Next
    INDEX
    Explanations

    references to K-12 education and the related challenges and inequalities

    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
     penalty
    -0.07
    کت
    -0.07
    arte
    -0.06
     function
    -0.06
    teri
    -0.06
     Penalty
    -0.06
    edback
    -0.06
    yn
    -0.06
    iva
    -0.06
     coast
    -0.06
    POSITIVE LOGITS
    nothrow
    0.08
    ennen
    0.07
    ardware
    0.07
     BSD
    0.07
    BuilderFactory
    0.07
    erver
    0.06
    YPRE
    0.06
    룴
    0.06
    ÑĸÑģÑĤ
    0.06
    loat
    0.06
    Activations Density 0.004%

    No Known Activations