© 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. 9-LLAMASCOPE-RES-131K
    11. 96377
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "town."

    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
    orgia
    -0.07
    اض
    -0.06
    deaux
    -0.06
    amd
    -0.06
    urve
    -0.06
    ieve
    -0.06
     pog
    -0.06
    rawler
    -0.06
    ylland
    -0.06
    ditor
    -0.06
    POSITIVE LOGITS
     grátis
    0.07
    /on
    0.07
    ivery
    0.07
    aset
    0.07
    geh
    0.06
    aan
    0.06
    ships
    0.06
    ãĥ©ãĥĥãĤ¯
    0.06
    chner
    0.06
     vÃŃc
    0.06
    Activations Density 0.005%

    No Known Activations