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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 104702
    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
     Trojan
    -0.06
    ique
    -0.06
    ç²ī
    -0.06
    Tro
    -0.06
     Statement
    -0.05
     ment
    -0.05
    Dlg
    -0.05
    STALL
    -0.05
    _pow
    -0.05
     Hogan
    -0.05
    POSITIVE LOGITS
     disadv
    0.07
    ebra
    0.07
    EDI
    0.07
    lesc
    0.07
    yleft
    0.07
    856
    0.06
     OTHERWISE
    0.06
    _IOCTL
    0.06
    iert
    0.06
    errupted
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.