© 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. 60528
    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
    erah
    -0.07
    enschaft
    -0.07
    InstantiationException
    -0.07
    abwe
    -0.07
    Ø´ÙĪر
    -0.07
    oreach
    -0.07
    leigh
    -0.07
    .Inst
    -0.07
    reachable
    -0.07
    subst
    -0.07
    POSITIVE LOGITS
     assorted
    0.06
    +++
    0.06
    169
    0.06
     elites
    0.06
    ipur
    0.06
    ied
    0.06
     Dien
    0.06
     Left
    0.05
     periodic
    0.05
    ences
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.