© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 15925
    Prev
    Next
    INDEX
    Explanations

    emotional connections and relationships expressed in the text

    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
    ungeons
    -0.07
    ystack
    -0.07
    orde
    -0.07
     ÐĿаÑģ
    -0.07
    .Thread
    -0.07
     Seah
    -0.07
    ÑģÑĮке
    -0.06
    erras
    -0.06
    Ñĩе
    -0.06
    cheng
    -0.06
    POSITIVE LOGITS
     relationship
    0.07
    compat
    0.06
    _relationship
    0.06
    ince
    0.06
     Relationship
    0.06
     abusive
    0.06
    relationship
    0.06
    ayas
    0.06
    435
    0.06
    948
    0.06
    Activations Density 0.018%

    No Known Activations