© 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. 78803
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    -0.08
    erap
    -0.07
    olet
    -0.07
    /www
    -0.07
    ãĤ·ãĤ§
    -0.07
    usion
    -0.06
    atcher
    -0.06
     programmes
    -0.06
    олеÑĤ
    -0.06
    859
    -0.06
    POSITIVE LOGITS
    croll
    0.07
    onal
    0.06
    важа
    0.06
    cellent
    0.06
    oa
    0.06
    CPF
    0.06
    urus
    0.06
     phục
    0.06
    idan
    0.06
    اذ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.