© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 61449
    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
     Ruth
    -0.06
    EQ
    -0.06
    atable
    -0.05
    ă
    -0.05
    emap
    -0.05
     rotten
    -0.05
     nues
    -0.05
    ¤
    -0.05
     Bis
    -0.05
     distortion
    -0.05
    POSITIVE LOGITS
    umo
    0.07
    crypto
    0.07
    izace
    0.07
    ieu
    0.07
     IDX
    0.07
    ewn
    0.07
     defaultManager
    0.07
    omic
    0.06
    anal
    0.06
    ÙĨاÙĨ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.