© 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. 123841
    Prev
    Next
    INDEX
    Explanations

    references to parental figures and their impact on the individual

    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
     his
    -0.07
    avic
    -0.06
     itself
    -0.06
     Himself
    -0.06
     himself
    -0.06
    abra
    -0.06
    ÑĸÑĪ
    -0.06
    forth
    -0.06
     sacred
    -0.06
    unga
    -0.06
    POSITIVE LOGITS
    eral
    0.08
    -child
    0.07
    /gr
    0.07
     byli
    0.07
     themselves
    0.07
    ekli
    0.07
    親
    0.07
    èle
    0.07
    ially
    0.07
    hoo
    0.07
    Activations Density 0.013%

    No Known Activations