© 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. 76543
    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
    anye
    -0.08
    odiac
    -0.07
    ÅĻes
    -0.07
    ži
    -0.07
    ãģŁãĤģãģ®
    -0.07
    ALLY
    -0.07
    notated
    -0.07
     thôi
    -0.07
    ìļ±
    -0.07
    oppel
    -0.07
    POSITIVE LOGITS
     reverse
    0.07
     Maj
    0.07
     linked
    0.06
     US
    0.06
    upp
    0.06
     j
    0.06
     till
    0.06
     Guar
    0.06
     Lar
    0.06
     "
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.