© 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. 60798
    Prev
    Next
    INDEX
    Explanations

    monetary values and pricing information

    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
    enburg
    -0.06
    ellen
    -0.06
    .il
    -0.06
     circ
    -0.06
    inerary
    -0.06
    azon
    -0.06
    мÑı
    -0.06
    reck
    -0.06
    enberg
    -0.06
    item
    -0.05
    POSITIVE LOGITS
     property
    0.09
     Property
    0.08
    _walk
    0.07
    Property
    0.07
    MLS
    0.07
    .Property
    0.07
    -property
    0.07
     PROPERTY
    0.07
    ulumi
    0.07
     MLS
    0.07
    Activations Density 0.003%

    No Known Activations