© 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. 1271
    Prev
    Next
    INDEX
    Explanations

    references to genetic concepts and their role in traits and attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     ngang
    -0.08
    elas
    -0.08
    urette
    -0.07
    dech
    -0.07
    reste
    -0.07
    .Elements
    -0.07
     ruce
    -0.07
    ulace
    -0.07
    mant
    -0.07
    edik
    -0.07
    POSITIVE LOGITS
     K
    0.06
     Cargo
    0.06
     k
    0.06
     Cl
    0.06
    ars
    0.06
    >Action
    0.06
     clusters
    0.05
     likely
    0.05
     identified
    0.05
     cargo
    0.05
    Activations Density 0.030%

    No Known Activations