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

    Neuronpedia

    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. 17089
    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
    ums
    -0.07
    ftp
    -0.07
    anki
    -0.07
    Ļ
    -0.07
     Pod
    -0.06
    adge
    -0.06
    cour
    -0.06
    quot
    -0.06
    lies
    -0.06
    boo
    -0.06
    POSITIVE LOGITS
    Ctl
    0.07
    pert
    0.07
    Disposed
    0.07
    ,$_
    0.06
    .times
    0.06
    ãģ¾ãĤĬ
    0.06
    \Redirect
    0.06
    openh
    0.06
    .scalablytyped
    0.06
     Ritch
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.