© 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. 15-LLAMASCOPE-RES-131K
    11. 88341
    Prev
    Next
    INDEX
    Explanations

    references to legal confessions and their validity

    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
    905
    -0.07
    876
    -0.06
    imon
    -0.06
    ived
    -0.06
    á»ijt
    -0.06
    SR
    -0.06
    _MB
    -0.06
    oto
    -0.06
    scal
    -0.06
    714
    -0.05
    POSITIVE LOGITS
     addCriterion
    0.07
    hoff
    0.07
    _putchar
    0.06
    ACES
    0.06
     SetValue
    0.06
    ureau
    0.06
    ÑģÑĤÑİ
    0.06
     Facility
    0.06
    FLOW
    0.06
    facility
    0.06
    Activations Density 0.039%

    No Known Activations