© 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. 17-LLAMASCOPE-RES-131K
    6. 76381
    Prev
    Next
    INDEX
    Explanations

    instances of monitoring and parental guidance in various contexts

    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
     olsun
    -0.08
    ẩn
    -0.08
    Ñĩини
    -0.07
    ाहà¤ķ
    -0.07
    oga
    -0.07
    edback
    -0.07
    ãģ»ãģ©
    -0.07
     tạm
    -0.07
    onde
    -0.07
     basit
    -0.07
    POSITIVE LOGITS
     disob
    0.09
     bypass
    0.09
     ignored
    0.09
     defiance
    0.08
     disreg
    0.08
     disobed
    0.08
     circum
    0.08
     continued
    0.08
     violation
    0.08
     violations
    0.08
    Activations Density 0.035%

    No Known Activations