© 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 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. 130234
    Prev
    Next
    INDEX
    Explanations

    references to mental health conditions and societal perceptions

    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
    ereotype
    -0.08
    eydi
    -0.07
    ãĥ¶
    -0.07
    ollo
    -0.07
    ifar
    -0.07
    neutral
    -0.07
    пеÑĩ
    -0.07
    æ©ĭ
    -0.07
    ulla
    -0.07
    /theme
    -0.07
    POSITIVE LOGITS
     laz
    0.07
     lifestyle
    0.07
     dev
    0.06
     fault
    0.06
     moral
    0.06
     inconvenient
    0.06
     caused
    0.06
     caus
    0.06
     management
    0.05
     weakness
    0.05
    Activations Density 0.012%

    No Known Activations