© 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. 69618
    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
    .construct
    -0.07
    Extern
    -0.07
     Evolution
    -0.07
    Facade
    -0.06
     reun
    -0.06
     separat
    -0.06
    491
    -0.06
     evolution
    -0.06
     hadn
    -0.06
     Crowley
    -0.06
    POSITIVE LOGITS
    ebin
    0.08
    spaces
    0.07
    bris
    0.07
    addons
    0.07
    esium
    0.07
    ibur
    0.07
     suspension
    0.07
    ernaut
    0.07
    iami
    0.07
    aternity
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.