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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 80031
    Prev
    Next
    INDEX
    Explanations

    interactions involving personal relationships and emotional responses

    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
    ä¸Ī夫
    -0.10
     masculine
    -0.07
     мÑĥжÑĩин
    -0.07
     males
    -0.07
     koc
    -0.07
     mascul
    -0.07
     male
    -0.06
    FromClass
    -0.06
    1
    -0.06
    2
    -0.06
    POSITIVE LOGITS
     Ms
    0.09
    ufen
    0.08
     Mrs
    0.08
    妻
    0.08
    Mrs
    0.08
    еÑĢи
    0.07
    erral
    0.07
     dames
    0.07
    Ms
    0.07
    夫人
    0.07
    Activations Density 0.619%

    No Known Activations