© 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. 17008
    Prev
    Next
    INDEX
    Explanations

    keywords related to asylum and refugee status

    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
    yu
    -0.07
    \Mapping
    -0.07
    iage
    -0.07
    ãģĦãģĨ
    -0.07
     Habitat
    -0.07
    apan
    -0.07
     kli
    -0.07
    andon
    -0.06
    odoxy
    -0.06
     mastur
    -0.06
    POSITIVE LOGITS
     seekers
    0.08
     seeker
    0.08
     Seek
    0.07
    dan
    0.07
    ÑĢоп
    0.07
     SEEK
    0.06
    Å¡ek
    0.06
    벨
    0.06
    seek
    0.06
    Seek
    0.06
    Activations Density 0.002%

    No Known Activations