© 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. 2679
    Prev
    Next
    INDEX
    Explanations

    phrases related to lack of consent and impositions on personal will

    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
    HR
    -0.07
    зÑĮ
    -0.07
    iban
    -0.07
    hsi
    -0.07
    Ñıж
    -0.07
    liable
    -0.07
    ismet
    -0.07
    orman
    -0.07
    ucu
    -0.06
     Bot
    -0.06
    POSITIVE LOGITS
     unwanted
    0.12
     consent
    0.09
     undes
    0.07
     wanted
    0.07
     Consent
    0.07
     unwilling
    0.07
     involuntary
    0.06
     wishes
    0.06
     Wanted
    0.06
    wanted
    0.06
    Activations Density 0.039%

    No Known Activations