© 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 EvalsExportsAPI 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. 130239
    Prev
    Next
    INDEX
    Explanations

    concepts related to social reintegration and second chances for offenders

    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
    itler
    -0.08
    uters
    -0.07
    loth
    -0.07
    acht
    -0.07
    arger
    -0.06
     morally
    -0.06
    ADS
    -0.06
    cf
    -0.06
    allel
    -0.06
    iske
    -0.06
    POSITIVE LOGITS
     rates
    0.07
    ìľ¨
    0.07
    çİĩ
    0.07
    GGLE
    0.07
    -through
    0.06
     Rates
    0.06
     rate
    0.06
    -rate
    0.06
    rate
    0.06
    heim
    0.06
    Activations Density 0.017%

    No Known Activations