© 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. 104608
    Prev
    Next
    INDEX
    Explanations

    phrases indicating respect for confidentiality and anonymity

    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
     Bene
    -0.08
     MHz
    -0.07
    å¼
    -0.07
    егоÑĢ
    -0.06
    ync
    -0.06
    £½
    -0.06
    ymes
    -0.06
    ska
    -0.06
    TF
    -0.06
    indle
    -0.06
    POSITIVE LOGITS
     confidentiality
    0.17
     privacy
    0.16
     confidential
    0.15
     Privacy
    0.14
    Privacy
    0.14
     Confidential
    0.13
    privacy
    0.13
     secrecy
    0.10
     HIP
    0.10
     discretion
    0.09
    Activations Density 0.075%

    No Known Activations