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

    Neuronpedia

    Jacobian LensNEW
    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. 57413
    Prev
    Next
    INDEX
    Explanations

    phrases that address the reader directly with a focus on providing information or guidance

    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
    ypi
    -0.06
     ведÑĮ
    -0.06
    claimer
    -0.06
    ypo
    -0.06
    Bron
    -0.06
    cq
    -0.06
    POS
    -0.06
    UPLE
    -0.06
    cope
    -0.06
    awan
    -0.06
    POSITIVE LOGITS
     missed
    0.08
     STDCALL
    0.07
     Abed
    0.07
     Exped
    0.07
    Æł
    0.07
    .IContainer
    0.07
     tuyá»ĩt
    0.07
    _tac
    0.06
    ande
    0.06
    ëĵł
    0.06
    Activations Density 0.007%

    No Known Activations