© 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. 27124
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and governance issues

    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
    grese
    -0.09
    ॰
    -0.08
    OffsetTable
    -0.08
    PÅĻed
    -0.08
    ACTER
    -0.08
    ANNER
    -0.08
    ÏĦοÏħÏĤ
    -0.08
     ÙĪÛĮÚĺ
    -0.08
    itia
    -0.08
    LayoutConstraint
    -0.08
    POSITIVE LOGITS
     existing
    0.10
     other
    0.10
     or
    0.10
     remaining
    0.08
     already
    0.08
     pending
    0.07
    existing
    0.07
     de
    0.07
    other
    0.07
     mentioned
    0.06
    Activations Density 0.023%

    No Known Activations