© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3346
    Prev
    Next
    INDEX
    Explanations

    structured phrases related to legal and operational aspects

    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
    [
    -0.07
    ister
    -0.07
    (-
    -0.06
    (
    -0.06
    ber
    -0.05
     (
    -0.05
    751
    -0.05
     Kuwait
    -0.05
    --
    -0.05
    2
    -0.05
    POSITIVE LOGITS
    Ctrls
    0.10
    NotificationCenter
    0.10
    Ñģклад
    0.08
     addCriterion
    0.08
    ItemImage
    0.08
    .vocab
    0.08
    _utilities
    0.08
    .IContainer
    0.08
    ProcAddress
    0.08
    pets
    0.08
    Activations Density 0.207%

    No Known Activations