© 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. 29141
    Prev
    Next
    INDEX
    Explanations

    references to upbringing and familial 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
     Pregn
    -0.08
    rescia
    -0.07
     äl
    -0.07
    ipp
    -0.07
     Pregnancy
    -0.07
     пеÑĢеÑģ
    -0.06
     Fus
    -0.06
    oden
    -0.06
     pregnant
    -0.06
     Fuse
    -0.06
    POSITIVE LOGITS
     upbringing
    0.15
     childhood
    0.14
     growing
    0.12
     Childhood
    0.11
     Growing
    0.10
     grew
    0.10
     Raised
    0.10
    Raised
    0.10
     raised
    0.10
     grows
    0.09
    Activations Density 0.160%

    No Known Activations