© 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. 128049
    Prev
    Next
    INDEX
    Explanations

    numerical values and measurements related to lists and quantities

    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
     away
    -0.07
     rival
    -0.06
     help
    -0.06
     personal
    -0.06
     may
    -0.06
    еÑģÑĤи
    -0.06
     or
    -0.06
    an
    -0.06
     will
    -0.06
     your
    -0.06
    POSITIVE LOGITS
    evin
    0.08
    constitution
    0.08
    abox
    0.07
    éijij
    0.07
    _exact
    0.07
    undy
    0.07
    ideshow
    0.07
    ViewState
    0.07
    .DataBind
    0.07
    utton
    0.07
    Activations Density 0.001%

    No Known Activations