© 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. 73668
    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
    ãĥ³ãĥĨãĤ£
    -0.07
    pone
    -0.07
    plx
    -0.07
    YTE
    -0.07
    ูà¸ģà¸Ħ
    -0.07
    abis
    -0.07
    ableObject
    -0.07
    aight
    -0.07
    acades
    -0.07
    ÎŃÏģγ
    -0.07
    POSITIVE LOGITS
    202
    0.08
    inal
    0.07
     Hib
    0.07
    se
    0.06
    ignon
    0.06
    anger
    0.06
    DI
    0.06
    201
    0.06
    -s
    0.06
    aden
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.