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. 95942
    Prev
    Next
    INDEX
    Explanations

    numerical values and statistics

    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
    èĵ
    -0.08
     flock
    -0.06
    dac
    -0.06
    elder
    -0.06
    nable
    -0.06
     Passion
    -0.06
    aca
    -0.06
    ario
    -0.06
    lein
    -0.06
    329
    -0.06
    POSITIVE LOGITS
    izza
    0.06
    ored
    0.06
    DT
    0.06
     calle
    0.06
    ukes
    0.06
    овиÑĩ
    0.06
    keh
    0.06
    hone
    0.06
    ire
    0.06
    ATS
    0.06
    Activations Density 0.000%

    No Known Activations