© 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. 16347
    Prev
    Next
    INDEX
    Explanations

    references to actions and policies related to technology regulation and international relations

    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
    ewood
    -0.07
    assin
    -0.07
    AtA
    -0.06
    âng
    -0.06
    ÑģÑĥ
    -0.06
    492
    -0.06
    _DH
    -0.06
    eti
    -0.06
    Workspace
    -0.06
    .GroupLayout
    -0.06
    POSITIVE LOGITS
    rou
    0.06
    ub
    0.06
    rs
    0.06
    itre
    0.06
     Optical
    0.06
    its
    0.06
    /edit
    0.06
    .app
    0.05
     Pry
    0.05
     opt
    0.05
    Activations Density 0.019%

    No Known Activations