© 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. 74597
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names related to locations or organizations

    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
    ften
    -0.07
    лада
    -0.07
    beros
    -0.07
    .FontStyle
    -0.07
    aign
    -0.07
    abus
    -0.07
    ancel
    -0.07
    Ñĸж
    -0.06
    aż
    -0.06
    eten
    -0.06
    POSITIVE LOGITS
    ugo
    0.07
    ãĥĨãĥ«
    0.06
    ularity
    0.06
    vig
    0.06
    Leaks
    0.06
    ãĥ³ãĤ°ãĥ«
    0.06
    erring
    0.06
    isci
    0.05
    thinkable
    0.05
    PLETED
    0.05
    Activations Density 0.031%

    No Known Activations