© 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. 95116
    Prev
    Next
    INDEX
    Explanations

    sequences indicating societal issues or injustices

    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
    -like
    -0.07
     dos
    -0.06
    ome
    -0.06
    esson
    -0.06
    276
    -0.06
    zioni
    -0.06
    ÑĮ
    -0.06
     free
    -0.06
    ocab
    -0.06
     definite
    -0.06
    POSITIVE LOGITS
     -*-č↵
    0.07
    'gc
    0.07
    ContentSize
    0.07
    $MESS
    0.07
    ArrayOf
    0.07
    ãĥ³ãĥĩ
    0.07
     è²
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    GuidId
    0.07
    ansi
    0.06
    Activations Density 0.083%

    No Known Activations