© 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. 73435
    Prev
    Next
    INDEX
    Explanations

    references to infidelity and cheating in 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
    asso
    -0.09
    assage
    -0.08
    éĻ
    -0.07
    gaard
    -0.07
    anager
    -0.07
    spd
    -0.07
    nett
    -0.07
    senal
    -0.07
    enser
    -0.07
    ofday
    -0.07
    POSITIVE LOGITS
     with
    0.07
     wives
    0.07
     wife
    0.06
    with
    0.06
     opportunity
    0.06
     vows
    0.05
     Opportunities
    0.05
     Eye
    0.05
    aken
    0.05
    monic
    0.05
    Activations Density 0.003%

    No Known Activations