© 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. 29913
    Prev
    Next
    INDEX
    Explanations

    geographical features, particularly names of lakes, rivers, and parks

    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
    VILLE
    -0.07
    ina
    -0.07
     River
    -0.06
    OF
    -0.06
    avana
    -0.06
    vail
    -0.06
    _ERRORS
    -0.06
    querque
    -0.06
    iname
    -0.06
    sic
    -0.06
    POSITIVE LOGITS
     Authority
    0.07
    поÑĩ
    0.06
     Shuffle
    0.06
    ÅĤo
    0.06
    adows
    0.06
    leme
    0.06
     Warren
    0.06
    weg
    0.06
    obble
    0.06
    çķ
    0.06
    Activations Density 0.061%

    No Known Activations