© 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. 83084
    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
    ereo
    -0.08
    ìĤ°
    -0.07
    rv
    -0.06
    éĴŁ
    -0.06
     demanding
    -0.06
    ارÙĩ
    -0.06
     impacted
    -0.06
    ìĿ´ê°Ģ
    -0.06
    chin
    -0.06
    .Mod
    -0.06
    POSITIVE LOGITS
    adÃŃ
    0.08
    cid
    0.07
    ÃŃk
    0.07
     GDK
    0.06
    ennent
    0.06
    exe
    0.06
    ulas
    0.06
    iges
    0.06
    ãģĵãĤĵãģ«ãģ¡ãģ¯
    0.06
    ycastle
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.