Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 93766
    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
    .nom
    -0.07
     phúc
    -0.07
    alc
    -0.06
    ousse
    -0.06
    .opensource
    -0.06
    ãĥ¼ãĥIJ
    -0.06
    Outlined
    -0.06
     vÃŃ
    -0.06
    èİ
    -0.06
    à¥įथन
    -0.06
    POSITIVE LOGITS
    mpl
    0.06
    amura
    0.06
    adies
    0.06
    apphire
    0.06
     заÑģ
    0.06
    urry
    0.06
     Hazel
    0.06
     Canadian
    0.06
     Portfolio
    0.05
     Greenwood
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.