© 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. 126663
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and dynamics

    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
    ÅĤÄħ
    -0.09
    orst
    -0.08
    ALSE
    -0.08
    .qual
    -0.08
    ÙĤب
    -0.08
    uron
    -0.07
    znám
    -0.07
    stüt
    -0.07
     dÅĻÃŃ
    -0.07
    uts
    -0.07
    POSITIVE LOGITS
     pre
    0.07
     ages
    0.07
     blind
    0.07
     Inf
    0.07
     late
    0.06
     mini
    0.06
     age
    0.06
     newly
    0.06
     younger
    0.06
     plan
    0.06
    Activations Density 0.005%

    No Known Activations