© 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. 29842
    Prev
    Next
    INDEX
    Explanations

    roles and titles associated with advocacy and leadership

    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
    IRON
    -0.08
    ERM
    -0.08
    edis
    -0.07
    olvers
    -0.07
    amm
    -0.07
    ÑĸллÑı
    -0.07
    owell
    -0.07
    isma
    -0.07
    HOOK
    -0.07
    CX
    -0.07
    POSITIVE LOGITS
     who
    0.08
     for
    0.07
     whose
    0.07
     among
    0.06
    ipping
    0.06
    IPPING
    0.06
     whom
    0.06
     bagi
    0.06
     both
    0.06
     amongst
    0.06
    Activations Density 0.022%

    No Known Activations