© 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. 126816
    Prev
    Next
    INDEX
    Explanations

    key phrases related to regulations and compliance in education or business contexts

    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
    igham
    -0.07
     DevComponents
    -0.07
    zac
    -0.07
    SystemService
    -0.07
     reuseIdentifier
    -0.07
    rowsable
    -0.07
    PLIC
    -0.07
    rif
    -0.07
    :UITableView
    -0.07
    GetProperty
    -0.07
    POSITIVE LOGITS
     Minor
    0.06
     Moh
    0.06
    1
    0.06
    .ht
    0.06
     _
    0.06
     tort
    0.06
     Oper
    0.06
    otti
    0.06
     mol
    0.06
    linky
    0.05
    Activations Density 0.046%

    No Known Activations