© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 74884
    Prev
    Next
    INDEX
    Explanations

    numeric patterns, especially those related to identifiers or coding

    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
    ../../../
    -0.10
    -quarters
    -0.08
    st
    -0.08
    ../../../../
    -0.07
    ../../
    -0.07
    ties
    -0.07
    -quarter
    -0.07
    رس
    -0.07
    rd
    -0.07
    fold
    -0.06
    POSITIVE LOGITS
    nd
    0.10
    ãĥ¼ãĥĦ
    0.09
    ndx
    0.08
    åĿª
    0.07
    .WinForms
    0.07
    idon
    0.07
    _ACL
    0.07
    nds
    0.07
    uelles
    0.07
     tay
    0.07
    Activations Density 0.075%

    No Known Activations