© 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. 15-LLAMASCOPE-RES-131K
    11. 529
    Prev
    Next
    INDEX
    Explanations

    themes of psychological well-being and positive experiences

    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
    .bc
    -0.07
    emy
    -0.07
    423
    -0.07
    мÑĭ
    -0.07
    usercontent
    -0.06
    æIJŃ
    -0.06
    agal
    -0.06
    _permission
    -0.06
    mux
    -0.06
     pev
    -0.06
    POSITIVE LOGITS
     versus
    0.07
     vs
    0.07
     cert
    0.06
     certain
    0.06
     Lad
    0.06
     Certain
    0.06
    rop
    0.06
    ucene
    0.06
    Certain
    0.06
    .hw
    0.06
    Activations Density 0.016%

    No Known Activations