© 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. 14684
    Prev
    Next
    INDEX
    Explanations

    demographic information or statistics relating to population sizes

    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
    indsight
    -0.07
    seau
    -0.07
    illon
    -0.07
    วà¸Ļ
    -0.07
    uada
    -0.07
    PFN
    -0.07
    سب
    -0.07
    .nz
    -0.07
    ħį
    -0.07
     Widow
    -0.07
    POSITIVE LOGITS
     population
    0.10
     city
    0.09
    population
    0.08
     living
    0.07
     town
    0.07
     Population
    0.07
     inhabitants
    0.07
     ÙĨسÙħØ©
    0.07
    Population
    0.06
     permanent
    0.06
    Activations Density 0.016%

    No Known Activations