© 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. 26615
    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
    orno
    -0.07
    posites
    -0.07
    çĢ¬
    -0.06
     Skull
    -0.06
    arget
    -0.06
    áli
    -0.06
    illas
    -0.06
    oad
    -0.06
    \Field
    -0.06
    .springboot
    -0.06
    POSITIVE LOGITS
     tô
    0.07
    aklı
    0.06
     your
    0.06
    ruba
    0.06
     minim
    0.06
    dehy
    0.06
    AGO
    0.06
     concent
    0.06
    OUCH
    0.06
    亿åħĥ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.