© 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. 15-LLAMASCOPE-RES-131K
    11. 62395
    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
    ROTO
    -0.07
    ajar
    -0.07
    arkan
    -0.07
    noinspection
    -0.07
    479
    -0.06
     pound
    -0.06
    559
    -0.06
    .googlecode
    -0.06
    alen
    -0.06
     resume
    -0.06
    POSITIVE LOGITS
    ĽĦ
    0.07
    Äĥn
    0.07
    Tp
    0.06
    /trunk
    0.06
    relu
    0.06
     slowed
    0.06
    .Direct
    0.06
    mass
    0.06
     dep
    0.06
     owed
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.