© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29538
    Prev
    Next
    INDEX
    Explanations

    names of individuals associated with academic or professional qualifications

    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
    ÄŁan
    -0.07
    iasi
    -0.07
    amina
    -0.07
     odv
    -0.07
    DAQ
    -0.07
    chartInstance
    -0.07
    ané
    -0.07
    atin
    -0.06
    daq
    -0.06
    foon
    -0.06
    POSITIVE LOGITS
     PhD
    0.08
     Jr
    0.06
     III
    0.06
     ÃIJ
    0.06
     Ph
    0.06
    affen
    0.06
    ikip
    0.06
    appen
    0.06
     Sc
    0.06
    DRV
    0.06
    Activations Density 0.017%

    No Known Activations