© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 5-LLAMASCOPE-RES-131K
    11. 126523
    Prev
    Next
    INDEX
    Explanations

    references to human emotions and relationships

    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
     addCriterion
    -0.07
    ÄŁan
    -0.07
    gaard
    -0.07
    uner
    -0.07
    VersionUID
    -0.07
    nici
    -0.07
    ̣
    -0.07
     IonicModule
    -0.07
    ibold
    -0.07
    itelist
    -0.07
    POSITIVE LOGITS
     disin
    0.07
    577
    0.05
     piece
    0.05
     Sanchez
    0.05
    rick
    0.05
    owitz
    0.05
    166
    0.05
     Rut
    0.05
     skip
    0.05
    ashes
    0.05
    Activations Density 0.014%

    No Known Activations