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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5427
    Prev
    Next
    INDEX
    Explanations

    terms related to social issues and criticisms of leadership accountability

    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
    ãĥ¼ãĥ«ãĥī
    -0.07
    agle
    -0.06
    ccione
    -0.06
     captivity
    -0.06
     peasants
    -0.06
     Sith
    -0.06
    çĭ
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    hong
    -0.06
    AppState
    -0.06
    POSITIVE LOGITS
     Immigration
    0.10
     Integration
    0.10
     immigration
    0.10
    -imm
    0.10
     immigrants
    0.10
     immigrant
    0.10
    Integration
    0.09
     Migration
    0.09
    Imm
    0.09
     Imm
    0.09
    Activations Density 0.042%

    No Known Activations