© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 16324
    Prev
    Next
    INDEX
    Explanations

    the phrase "per," indicating references to policies or guidelines related to rules or regulations

    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
    oretical
    -0.08
    ominator
    -0.08
    à¥ģà¤Ĩ
    -0.07
    ariant
    -0.07
    ecko
    -0.07
     getField
    -0.07
    ADED
    -0.07
    elerik
    -0.06
    /or
    -0.06
     Lumpur
    -0.06
    POSITIVE LOGITS
     the
    0.10
    iphery
    0.08
     their
    0.08
     usual
    0.08
     our
    0.08
     rules
    0.07
     its
    0.07
    ìĦł
    0.06
     below
    0.06
     this
    0.06
    Activations Density 0.003%

    No Known Activations