Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77155
    Prev
    Next
    INDEX
    Explanations

    discussions on societal norms, morality, and cultural supremacy

    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
    razil
    -0.09
    ambre
    -0.08
    дем
    -0.08
    .instant
    -0.07
    hausen
    -0.07
    ÙĪØ²ÛĮ
    -0.07
    FileVersion
    -0.07
    Ø®
    -0.07
    _migration
    -0.07
    ["$
    -0.07
    POSITIVE LOGITS
    alen
    0.07
     _
    0.07
     those
    0.06
     nature
    0.06
     so
    0.06
    ursively
    0.06
     importantly
    0.06
    ips
    0.06
     themselves
    0.05
    umeric
    0.05
    Activations Density 0.024%

    No Known Activations