© 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. 124662
    Prev
    Next
    INDEX
    Explanations

    themes related to parental custody 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
    ixin
    -0.09
    /***/
    -0.08
    atron
    -0.08
    phans
    -0.07
    inherits
    -0.07
    #End
    -0.07
     Rosenstein
    -0.07
    rrha
    -0.07
    daq
    -0.07
    unan
    -0.07
    POSITIVE LOGITS
     nut
    0.06
     Nut
    0.06
    ne
    0.06
     Lionel
    0.06
     unstable
    0.06
    aine
    0.06
     rev
    0.05
    ilit
    0.05
     court
    0.05
     hearing
    0.05
    Activations Density 0.026%

    No Known Activations