© 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. 17-LLAMASCOPE-RES-131K
    11. 74547
    Prev
    Next
    INDEX
    Explanations

    looping structures and iteration statements in code

    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
     ÑĸменÑĸ
    -0.08
    landırma
    -0.07
    oggler
    -0.07
     NONE
    -0.07
    ekil
    -0.07
     Stateless
    -0.07
    ibus
    -0.07
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.07
    .Invariant
    -0.07
    )(__
    -0.07
    POSITIVE LOGITS
     range
    0.06
    IPH
    0.06
     Philipp
    0.06
    jaw
    0.06
    ìŀIJ
    0.06
    creasing
    0.06
    orge
    0.05
    ÑĢÑİ
    0.05
    .Iterator
    0.05
    URE
    0.05
    Activations Density 0.004%

    No Known Activations