© 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. 128000
    Prev
    Next
    INDEX
    Explanations

    texts that include time stamps or dates

    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
    ARS
    -0.06
    wis
    -0.06
    ypo
    -0.06
    upyter
    -0.06
     rec
    -0.06
    \Active
    -0.06
    éĢŁ
    -0.06
    olla
    -0.06
    .ml
    -0.06
    Ī¬
    -0.05
    POSITIVE LOGITS
    اÙĤ
    0.07
    ãģ°ãģĭãĤĬ
    0.07
    aign
    0.06
    asses
    0.06
    Äļ
    0.06
    ORIZATION
    0.06
    ÄĽle
    0.06
    ÙĨدÛĮ
    0.06
    ALSE
    0.06
    /autoload
    0.06
    Activations Density 0.001%

    No Known Activations