© 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. 124857
    Prev
    Next
    INDEX
    Explanations

    terms related to polyamory and relationship structures

    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
    quals
    -0.08
    ãĤ¤ãĥ³ãĥĪ
    -0.08
    ABCDEFG
    -0.08
    quo
    -0.08
    atak
    -0.08
    iggers
    -0.07
    ifact
    -0.07
    oland
    -0.07
    mez
    -0.07
    _recovery
    -0.07
    POSITIVE LOGITS
    poly
    0.07
     poly
    0.07
     Poly
    0.07
     relationships
    0.07
     mon
    0.06
     Bash
    0.06
     multi
    0.06
     Relationships
    0.06
    /div
    0.06
     multiple
    0.06
    Activations Density 0.003%

    No Known Activations