© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 57466
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and estimates related to financial performance

    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
     nextState
    -0.06
    ama
    -0.06
    added
    -0.06
    ecd
    -0.06
    lesia
    -0.06
     omn
    -0.06
    ÏģÏīÏĥη
    -0.06
    Ha
    -0.05
    ilig
    -0.05
    uong
    -0.05
    POSITIVE LOGITS
    Margins
    0.07
    URRENT
    0.07
    atum
    0.07
    eniable
    0.07
    łí
    0.07
    tres
    0.07
    luž
    0.06
    ÑĸйÑģ
    0.06
    imus
    0.06
    μαÏĦο
    0.06
    Activations Density 0.003%

    No Known Activations