© 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 EvalsExportsinterp-engineNEWAPI 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. 120344
    Prev
    Next
    INDEX
    Explanations

    references to academic or professional roles and their associated responsibilities

    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
    ey
    -0.07
    ообÑĢаз
    -0.07
    engeance
    -0.07
    ãĤĦ
    -0.07
    تس
    -0.06
    .shiro
    -0.06
    ãģłãģijãģ§
    -0.06
    Ñģо
    -0.06
     ãĤĦ
    -0.06
     صÙĨ
    -0.06
    POSITIVE LOGITS
     respectively
    0.13
     alike
    0.11
     combo
    0.09
    respect
    0.07
     depending
    0.07
     combination
    0.07
    kaar
    0.07
    depending
    0.07
    izes
    0.07
    (optional
    0.07
    Activations Density 0.137%

    No Known Activations