© 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. 71431
    Prev
    Next
    INDEX
    Explanations

    references to documentary photography and its creators

    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
    ehler
    -0.08
    kowski
    -0.07
    ibbean
    -0.07
    ertainment
    -0.07
    vider
    -0.07
    iropr
    -0.07
    hiba
    -0.07
    åŃĿ
    -0.07
    elian
    -0.07
    SCP
    -0.07
    POSITIVE LOGITS
     projects
    0.07
     proje
    0.07
     project
    0.07
     Projects
    0.06
     defined
    0.06
    à¹Ģหà¸Ļ
    0.06
     %[
    0.06
    Projects
    0.06
     Pie
    0.06
    projects
    0.06
    Activations Density 0.020%

    No Known Activations