© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 888
    Prev
    Next
    INDEX
    Explanations

    references to political authority and responsibilities

    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
    tero
    -0.07
    eda
    -0.07
    rio
    -0.07
    icast
    -0.07
    OKIE
    -0.07
    ayet
    -0.06
    ÑĥÑĢÑĭ
    -0.06
    bane
    -0.06
    eson
    -0.06
    dire
    -0.06
    POSITIVE LOGITS
     Yard
    0.07
    ertz
    0.07
     [$
    0.06
     optionally
    0.06
     Optionally
    0.06
     yard
    0.06
    ioms
    0.06
    irts
    0.06
    ForKey
    0.06
    [,]
    0.06
    Activations Density 0.031%

    No Known Activations