© 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. 89090
    Prev
    Next
    INDEX
    Explanations

    elements related to themes of marital relationships and infidelity

    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
    @(
    -0.07
    iedade
    -0.07
    zzle
    -0.07
    .office
    -0.07
    ampus
    -0.07
    Trivia
    -0.07
     Wilderness
    -0.07
    izik
    -0.07
    ieval
    -0.07
    adge
    -0.07
    POSITIVE LOGITS
    tron
    0.06
     upstream
    0.06
     Yankee
    0.06
     Bulletin
    0.06
     Pole
    0.06
    ifications
    0.05
     nicknamed
    0.05
     '');
    0.05
     Orient
    0.05
     Nordic
    0.05
    Activations Density 0.026%

    No Known Activations