© 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. 69478
    Prev
    Next
    INDEX
    Explanations

    names and titles related to individuals and entities

    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
    ighth
    -0.08
    Ā
    -0.08
    .GroupLayout
    -0.08
     имÑĥ
    -0.08
    кÑĢа
    -0.08
    iversit
    -0.07
    $MESS
    -0.07
    \Annotation
    -0.07
    erif
    -0.07
     addCriterion
    -0.07
    POSITIVE LOGITS
    orem
    0.08
    iese
    0.07
    ève
    0.07
    IPLE
    0.06
    atum
    0.06
    uropean
    0.06
    æ°ı
    0.06
    ãĢħ
    0.06
    k
    0.06
    ien
    0.06
    Activations Density 0.097%

    No Known Activations