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. 76602
    Prev
    Next
    INDEX
    Explanations

    themes related to social injustice and structures of oppression

    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
    ä¸ĺ
    -0.07
     population
    -0.07
    æĸ
    -0.07
    à¸Ľà¸£à¸°à¸Ĭ
    -0.07
    population
    -0.07
    ãĥIJãĤ¤
    -0.07
     motor
    -0.06
    hil
    -0.06
    人åı£
    -0.06
    è£ı
    -0.06
    POSITIVE LOGITS
     apartheid
    0.10
     Mandela
    0.09
    theid
    0.08
     segregation
    0.08
     McB
    0.07
     Rhodes
    0.07
    ystem
    0.07
    rana
    0.07
    anke
    0.07
     whites
    0.07
    Activations Density 0.055%

    No Known Activations