© 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. 77336
    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
    ylon
    -0.06
    omens
    -0.06
    ungi
    -0.06
     cardi
    -0.06
    uten
    -0.06
    alo
    -0.06
    acht
    -0.06
    rotch
    -0.06
    icket
    -0.06
    ungeons
    -0.06
    POSITIVE LOGITS
     mattress
    0.11
     mattresses
    0.09
     Matt
    0.08
    Matt
    0.08
    _bed
    0.08
     bed
    0.08
     Sleep
    0.08
    åºĬ
    0.07
     ÑĢеб
    0.07
     Bed
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.