© 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. 59481
    Prev
    Next
    INDEX
    Explanations

    phrases and questions related to knowledge and understanding

    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
    isbury
    -0.08
    isay
    -0.08
    cci
    -0.07
     McM
    -0.07
    ilogy
    -0.07
    QUENCE
    -0.07
    iphone
    -0.07
     عÙĨ
    -0.07
    ализи
    -0.07
     Bên
    -0.07
    POSITIVE LOGITS
    atform
    0.06
    rompt
    0.06
    e
    0.06
     pimp
    0.06
     stere
    0.06
    /I
    0.06
    culture
    0.06
    αιν
    0.06
     culture
    0.06
     Culture
    0.05
    Activations Density 0.036%

    No Known Activations