© 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. 16193
    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
    oproject
    -0.07
    tingham
    -0.07
    isoft
    -0.07
    odoxy
    -0.07
    ãĥįãĥ«
    -0.06
    ullet
    -0.06
    à¹ĩà¸ĩ
    -0.06
    agne
    -0.06
    uckle
    -0.06
    ucker
    -0.06
    POSITIVE LOGITS
    jak
    0.06
    èĬ¬
    0.06
    ãĢ
    0.06
    लà¤Ĺ
    0.06
    jay
    0.06
     Civ
    0.06
    adow
    0.06
    éĽĦ
    0.06
    社åĮº
    0.06
    âī¡
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.