© 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. 83953
    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
    iá»ģm
    -0.08
    lÃŃÄį
    -0.08
    alfa
    -0.08
    _Store
    -0.07
    istrovstvÃŃ
    -0.07
    ÙĦÙĥتر
    -0.07
     СШÐIJ
    -0.07
    USA
    -0.07
     WHATSOEVER
    -0.07
    ëĤĺëĿ¼
    -0.07
    POSITIVE LOGITS
    ensus
    0.06
    m
    0.06
    ouched
    0.06
    ichte
    0.06
    ffen
    0.06
     mimic
    0.05
    ightly
    0.05
    fov
    0.05
     dipl
    0.05
     reform
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.