© 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. 17-LLAMASCOPE-RES-131K
    11. 71416
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usage in sentences

    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
    ingles
    -0.06
    tones
    -0.06
    sut
    -0.06
     обÑĬ
    -0.06
    Ñīа
    -0.06
     Hood
    -0.06
    ston
    -0.06
    rens
    -0.06
    ael
    -0.06
    stants
    -0.06
    POSITIVE LOGITS
    adata
    0.08
     Marvin
    0.08
    outu
    0.06
    isode
    0.06
     ActiveForm
    0.06
     hall
    0.06
    akis
    0.06
    KHTML
    0.06
    ukan
    0.06
    trail
    0.06
    Activations Density 0.011%

    No Known Activations