© 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. 5035
    Prev
    Next
    INDEX
    Explanations

    phrases related to data collection and privacy policies

    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
    finity
    -0.07
    ç²
    -0.07
    ilip
    -0.07
    ableObject
    -0.07
    pit
    -0.07
    ãģ¹ãģ¦
    -0.07
     Eag
    -0.07
    Ð®ÐĽ
    -0.07
    CLA
    -0.06
     Moran
    -0.06
    POSITIVE LOGITS
    licht
    0.07
    .bc
    0.06
     opt
    0.06
    acob
    0.06
    kinson
    0.06
     mare
    0.06
    emm
    0.06
    ubar
    0.05
     bree
    0.05
     Frequency
    0.05
    Activations Density 0.001%

    No Known Activations