© 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. 9-LLAMASCOPE-RES-131K
    6. 95158
    Prev
    Next
    INDEX
    Explanations

    assignments or declarations of variables 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
    ساÙĨÛĮ
    -0.07
    imately
    -0.07
    ModelError
    -0.07
    dere
    -0.07
    .soft
    -0.07
    wrapped
    -0.07
    <strong
    -0.07
    prech
    -0.07
    dfa
    -0.06
    üzel
    -0.06
    POSITIVE LOGITS
     Albert
    0.07
     Aires
    0.07
    anki
    0.06
    ocker
    0.06
     Austin
    0.06
    _IOCTL
    0.05
    eriod
    0.05
     Carl
    0.05
    aits
    0.05
    Albert
    0.05
    Activations Density 0.010%

    No Known Activations