© 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 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. 56182
    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
    708
    -0.06
    PEND
    -0.06
    اÙĩÙħ
    -0.06
    Parallel
    -0.06
     revert
    -0.06
    ulus
    -0.06
     cig
    -0.06
    leta
    -0.06
    ereal
    -0.05
    427
    -0.05
    POSITIVE LOGITS
    retty
    0.08
    addon
    0.07
    Æ°Æ¡
    0.06
     encuent
    0.06
    oten
    0.06
    èĥ½å¤Ł
    0.06
    áºŃm
    0.06
    licos
    0.06
    -placeholder
    0.06
     Yine
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.