© 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 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. 74941
    Prev
    Next
    INDEX
    Explanations

    the concept of variability in different contexts

    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
    ISMATCH
    -0.08
    zon
    -0.08
    ska
    -0.07
    ity
    -0.07
    kah
    -0.06
    ordin
    -0.06
    urator
    -0.06
    system
    -0.06
    ses
    -0.06
    ereum
    -0.06
    POSITIVE LOGITS
     degrees
    0.14
    degrees
    0.12
     amounts
    0.10
     levels
    0.10
     depending
    0.09
     degree
    0.09
     amount
    0.09
    ç¨ĭ度
    0.08
     Degrees
    0.08
    amount
    0.08
    Activations Density 0.007%

    No Known Activations