© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82147
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in legal or official capacities, particularly in the context of responsibilities related to death and estate matters

    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
    SSERT
    -0.09
    Ñħа
    -0.08
    icorn
    -0.08
    pesan
    -0.08
    ỡ
    -0.08
    inki
    -0.08
    ARGS
    -0.08
    Äįel
    -0.08
     aalborg
    -0.07
    lernen
    -0.07
    POSITIVE LOGITS
     Authority
    0.07
     authority
    0.07
     acting
    0.06
    or
    0.06
    agan
    0.06
     unofficial
    0.05
     permanent
    0.05
     authorized
    0.05
    Authority
    0.05
     part
    0.05
    Activations Density 0.021%

    No Known Activations