© 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. 78032
    Prev
    Next
    INDEX
    Explanations

    mentions of countries or geographical locations

    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
     misd
    -0.07
    cene
    -0.07
    .CV
    -0.07
    ubat
    -0.06
     Král
    -0.06
    sWith
    -0.06
    FFE
    -0.06
    renc
    -0.06
    chez
    -0.06
     TestUtils
    -0.06
    POSITIVE LOGITS
    agher
    0.07
    ãĥªãĥ¼ãĤº
    0.07
    çģ
    0.06
     embargo
    0.06
     Lehr
    0.06
    terdam
    0.06
     Agents
    0.06
    atsby
    0.06
    erken
    0.06
    eview
    0.06
    Activations Density 0.030%

    No Known Activations