© 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. 130060
    Prev
    Next
    INDEX
    Explanations

    references to demographic data and statistics

    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
    arat
    -0.07
    .fields
    -0.07
    _matrices
    -0.07
    :eq
    -0.06
     Mata
    -0.06
    ằ
    -0.06
    nite
    -0.06
    ounce
    -0.06
    esz
    -0.06
    onta
    -0.06
    POSITIVE LOGITS
     trend
    0.07
     trends
    0.06
    ниÑĤ
    0.06
    _Osc
    0.06
    awah
    0.06
    471
    0.06
     ³³ ³³
    0.06
     evolution
    0.06
    sj
    0.06
    adel
    0.06
    Activations Density 0.003%

    No Known Activations