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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 5372
    Prev
    Next
    INDEX
    Explanations

    references to specific countries or geopolitical contexts

    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
    cano
    -0.07
    км
    -0.07
    hci
    -0.07
    eniz
    -0.07
    perator
    -0.06
     bag
    -0.06
    adera
    -0.06
     Bag
    -0.06
    šet
    -0.06
    utes
    -0.06
    POSITIVE LOGITS
     CNN
    0.08
    CNN
    0.07
    éĶĭ
    0.07
     ÑģÑĥ
    0.06
    zing
    0.06
    ami
    0.06
    NN
    0.06
    quoted
    0.06
    ATUS
    0.06
    _INITIALIZER
    0.06
    Activations Density 0.002%

    No Known Activations