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. 22-LLAMASCOPE-RES-131K
    6. 5274
    Prev
    Next
    INDEX
    Explanations

    references to the value of "H" in various contexts, indicating it is focused on high-tech industries or organizations

    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
    arrow
    -0.07
    orny
    -0.07
    ose
    -0.07
    orse
    -0.06
    imb
    -0.06
    ÃŃna
    -0.06
    -metadata
    -0.06
    ë£Į
    -0.06
    ल
    -0.06
    orm
    -0.06
    POSITIVE LOGITS
    //{{
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    engan
    0.07
    asso
    0.07
    esco
    0.06
    roc
    0.06
    rz
    0.06
    eci
    0.06
    üny
    0.06
    ÙĪÙĨت
    0.06
    Activations Density 0.021%

    No Known Activations