© 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. 119504
    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
    Äįe
    -0.07
    609
    -0.06
     Hur
    -0.06
    rift
    -0.06
     scalp
    -0.06
    ضÙĬ
    -0.06
    alama
    -0.06
    lev
    -0.05
    frauen
    -0.05
     ayak
    -0.05
    POSITIVE LOGITS
    ardon
    0.07
     minded
    0.06
    mmc
    0.06
    asures
    0.06
    Conv
    0.06
    179
    0.06
     even
    0.06
    лаÑĪ
    0.06
    Та
    0.06
    fonts
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.