© 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. 70855
    Prev
    Next
    INDEX
    Explanations

    phrases and structures related to instructions and guidance

    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
    restrict
    -0.07
    _restrict
    -0.07
    Resistance
    -0.07
    اÙħÛĮÙĨ
    -0.07
    REST
    -0.07
    buquerque
    -0.06
    restriction
    -0.06
    Peripheral
    -0.06
    .activate
    -0.06
    ctl
    -0.06
    POSITIVE LOGITS
     repeat
    0.12
     redo
    0.11
     repeats
    0.10
     re
    0.10
     Repeat
    0.10
     retry
    0.10
     повÑĤоÑĢ
    0.10
    repeat
    0.10
    éĩįæĸ°
    0.10
     retries
    0.09
    Activations Density 0.118%

    No Known Activations