© 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. 126691
    Prev
    Next
    INDEX
    Explanations

    discussions about parenting challenges and strategies

    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
     Vul
    -0.07
     ISO
    -0.07
    bis
    -0.06
     massive
    -0.06
    ois
    -0.06
    ائÙĬ
    -0.06
     veÅĻejné
    -0.06
     locker
    -0.06
    locker
    -0.06
     X
    -0.06
    POSITIVE LOGITS
     parenting
    0.08
    OptionsResolver
    0.07
     parent
    0.07
    pec
    0.07
    lava
    0.07
     temperament
    0.07
     paci
    0.07
     pac
    0.07
    pac
    0.07
    -parent
    0.07
    Activations Density 0.010%

    No Known Activations