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

    Neuronpedia

    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. 83357
    Prev
    Next
    INDEX
    Explanations

    structured data related to administrative units and statistics

    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
    erais
    -0.07
    vae
    -0.06
     uncon
    -0.06
     imported
    -0.06
    ublic
    -0.05
    ãĤ«ãĥ«
    -0.05
    tsky
    -0.05
     палÑĮ
    -0.05
     ActiveForm
    -0.05
     Jeg
    -0.05
    POSITIVE LOGITS
     statist
    0.07
     porr
    0.07
    gebn
    0.07
    >Data
    0.06
    Lens
    0.06
    .DataTable
    0.06
     demographic
    0.06
    population
    0.06
    ADATA
    0.06
    ByKey
    0.06
    Activations Density 0.019%

    No Known Activations