© 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. 119187
    Prev
    Next
    INDEX
    Explanations

    technical coding elements related to data management and configuration

    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
    .Mapping
    -0.09
    ÙĪÛĮÙĨت
    -0.09
    код
    -0.08
    #ad
    -0.08
    .kotlin
    -0.08
    .MixedReality
    -0.08
    ÑĢива
    -0.08
    koli
    -0.08
    .getElements
    -0.08
     -*-č↵
    -0.08
    POSITIVE LOGITS
    ueblo
    0.06
    ..↵
    0.06
    stantiateViewController
    0.06
    rais
    0.05
    voy
    0.05
    osh
    0.05
     Müller
    0.05
     inland
    0.05
    .
    0.05
    adh
    0.05
    Activations Density 0.295%

    No Known Activations