© 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. 84182
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate application, implementation, or applicability of 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
    obus
    -0.06
    GridColumn
    -0.06
    935
    -0.06
    ToProps
    -0.06
    ucu
    -0.06
    xdb
    -0.06
    ách
    -0.06
     chang
    -0.06
    adas
    -0.05
     Pew
    -0.05
    POSITIVE LOGITS
    oj
    0.08
    only
    0.08
    oya
    0.07
     only
    0.07
    aeda
    0.07
    ãģĤ
    0.07
     ONLY
    0.07
     wherever
    0.07
    eyJ
    0.06
    iful
    0.06
    Activations Density 0.004%

    No Known Activations