© 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. 9-LLAMASCOPE-RES-131K
    11. 97698
    Prev
    Next
    INDEX
    Explanations

    terms related to geopolitical entities or regions

    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
    ishes
    -0.08
    ish
    -0.07
    ird
    -0.07
    illes
    -0.06
    oo
    -0.06
    icles
    -0.06
    ox
    -0.06
    iles
    -0.06
    ican
    -0.06
    ourn
    -0.06
    POSITIVE LOGITS
    quiv
    0.07
    elsen
    0.07
    ãĤ¤ãĤº
    0.07
    VML
    0.07
    تاب
    0.07
    etak
    0.07
    åļ
    0.07
    askell
    0.07
    INGLE
    0.06
    rbrace
    0.06
    Activations Density 0.001%

    No Known Activations