© 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. 3328
    Prev
    Next
    INDEX
    Explanations

    concepts related to governance and accountability in societal systems

    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
    šť
    -0.06
    orde
    -0.05
    orf
    -0.05
    elt
    -0.05
     (*((
    -0.05
    upil
    -0.05
     moder
    -0.05
     Orig
    -0.05
     Naked
    -0.05
    gel
    -0.05
    POSITIVE LOGITS
    imers
    0.08
     actors
    0.07
    é¡ĺ
    0.07
    æļ
    0.07
     fuzz
    0.07
    еÑģÑı
    0.07
    itters
    0.07
    atsapp
    0.07
    ework
    0.07
    intl
    0.07
    Activations Density 0.001%

    No Known Activations