© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 59974
    Prev
    Next
    INDEX
    Explanations

    references to planning or making choices related to watching films and managing personal lists or goals

    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
    ìĬĪ
    -0.07
    kaar
    -0.07
    .AspNet
    -0.06
    ekl
    -0.06
     инÑĦоÑĢма
    -0.06
    thane
    -0.06
    ưu
    -0.06
    लब
    -0.06
    xa
    -0.06
    eware
    -0.06
    POSITIVE LOGITS
    defer
    0.07
    ieder
    0.07
    finally
    0.07
    Finally
    0.07
     remaining
    0.06
     backlog
    0.06
    Want
    0.06
     finally
    0.06
     Finally
    0.06
    Gap
    0.06
    Activations Density 0.031%

    No Known Activations