© 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 EvalsExportsinterp-engineNEWAPI 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. 42179
    Prev
    Next
    INDEX
    Explanations

    phrases related to policy and procedural specifications

    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
    ulty
    -0.07
     Pell
    -0.06
    achts
    -0.06
     Tet
    -0.06
    empt
    -0.06
    ught
    -0.06
     çĭ
    -0.06
    okus
    -0.06
    Ŀ
    -0.06
    adle
    -0.06
    POSITIVE LOGITS
    jo
    0.07
     pie
    0.07
    edin
    0.06
    irk
    0.06
    avit
    0.06
    etin
    0.06
    pie
    0.06
    OTION
    0.06
    าà¸Ĥ
    0.06
    bab
    0.06
    Activations Density 0.004%

    No Known Activations