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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 27135
    Prev
    Next
    INDEX
    Explanations

    elements related to web design or styling code

    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
    CharacterSet
    -0.07
    rots
    -0.07
     usern
    -0.06
    <dd
    -0.06
    URNS
    -0.06
    Rp
    -0.06
    ;element
    -0.06
    PELL
    -0.06
    ipher
    -0.06
    atürk
    -0.06
    POSITIVE LOGITS
    åľŃ
    0.07
    ague
    0.07
    .VisualBasic
    0.06
    ridge
    0.06
    efa
    0.06
     سÙĨت
    0.06
     Wolfe
    0.06
     households
    0.06
     Ritual
    0.06
     Boundary
    0.06
    Activations Density 0.002%

    No Known Activations