© 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. 62029
    Prev
    Next
    INDEX
    Explanations

    phrases related to serious social issues, particularly involving crime and victimization

    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
    .appspot
    -0.07
    oice
    -0.07
    strup
    -0.06
    заб
    -0.06
    ownik
    -0.06
    lech
    -0.06
     defe
    -0.06
    ajas
    -0.06
    ABI
    -0.06
    éĤ¦
    -0.06
    POSITIVE LOGITS
    çķ
    0.06
    boys
    0.06
    kowski
    0.06
    @student
    0.06
    ",{
    0.06
    ubl
    0.06
     Appalach
    0.06
    ophobia
    0.06
     Ruby
    0.06
    emos
    0.06
    Activations Density 0.001%

    No Known Activations