© 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. 86305
    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
     tract
    -0.08
    åĨĴ
    -0.06
    edula
    -0.06
    -i
    -0.06
    ãĥ¼ãĥĢ
    -0.06
    orro
    -0.06
    833
    -0.06
    ñana
    -0.06
    Scan
    -0.06
    enerative
    -0.06
    POSITIVE LOGITS
    kv
    0.07
    ysa
    0.06
     cur
    0.06
    evi
    0.06
    dü
    0.06
    件
    0.06
     kap
    0.06
    evin
    0.06
    UGC
    0.06
     Webb
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.