© 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. 87099
    Prev
    Next
    INDEX
    Explanations

    instances of specific phrases related to monetary values or awards

    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
    lobs
    -0.07
    ictim
    -0.06
    Programming
    -0.06
     Dere
    -0.06
     gro
    -0.06
     Nová
    -0.06
     dimensional
    -0.06
    ennis
    -0.06
    _Api
    -0.06
     Programming
    -0.05
    POSITIVE LOGITS
    odem
    0.07
    ágenes
    0.07
    овеÑĢ
    0.07
    Enlarge
    0.07
    juana
    0.06
     sust
    0.06
    bjerg
    0.06
    quete
    0.06
    quiv
    0.06
    bern
    0.06
    Activations Density 0.000%

    No Known Activations