© 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. 60391
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating possession or reference to individuals

    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
    ialog
    -0.08
     nackte
    -0.08
     سÛĮÙħ
    -0.07
    ICODE
    -0.07
    æĺ¯æĪij
    -0.07
    åİŁæĿ¥
    -0.07
    åĥķ
    -0.07
    [at
    -0.06
    [,]
    -0.06
    usat
    -0.06
    POSITIVE LOGITS
     Herr
    0.06
    ÑĢей
    0.06
     courtesy
    0.06
    ãĥ¼ãĥ¬
    0.06
    ilestone
    0.06
    ÑĢод
    0.06
    fds
    0.06
    unkt
    0.06
     Diss
    0.06
     oto
    0.06
    Activations Density 0.000%

    No Known Activations