© 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. 74973
    Prev
    Next
    INDEX
    Explanations

    reflections on personal mistakes and accountability for one's actions

    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
    ecz
    -0.08
     addCriterion
    -0.08
    lopen
    -0.07
    ndo
    -0.07
    loat
    -0.07
    uib
    -0.07
    uros
    -0.07
    izi
    -0.07
    Keywords
    -0.07
    vit
    -0.07
    POSITIVE LOGITS
     drugs
    0.07
     rational
    0.07
     actions
    0.07
     Rational
    0.07
     acting
    0.06
     behavior
    0.06
     drug
    0.06
     role
    0.06
     choices
    0.06
     part
    0.06
    Activations Density 0.030%

    No Known Activations