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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96124
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and authority

    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
    inka
    -0.07
    esar
    -0.07
    erge
    -0.07
    (es
    -0.07
    279
    -0.06
    479
    -0.06
    ÏĥμαÏĦα
    -0.06
     selfish
    -0.06
    076
    -0.06
     seins
    -0.06
    POSITIVE LOGITS
    atura
    0.07
    /tiny
    0.07
    onomy
    0.06
    ounsel
    0.06
     Moss
    0.06
    çŃĴ
    0.06
     Salv
    0.06
    нÑĮо
    0.06
    alice
    0.06
    coin
    0.05
    Activations Density 0.045%

    No Known Activations