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

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 88077
    Prev
    Next
    INDEX
    Explanations

    phrases related to control systems and their performance in technical contexts

    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
    iddet
    -0.07
    emd
    -0.07
     wards
    -0.06
     abnormalities
    -0.06
    .writeValue
    -0.06
    oref
    -0.06
    vik
    -0.06
    orro
    -0.06
    uele
    -0.06
     inconsist
    -0.06
    POSITIVE LOGITS
     Rica
    0.07
     optimal
    0.07
    untime
    0.07
    erno
    0.07
    ylon
    0.06
    angers
    0.06
    isay
    0.06
    layouts
    0.06
    맥
    0.06
     tá»iji
    0.06
    Activations Density 0.092%

    No Known Activations