© 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. 71245
    Prev
    Next
    INDEX
    Explanations

    terms related to data security and validation in programming contexts

    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
    ippi
    -0.08
    leck
    -0.08
    alion
    -0.08
    .scalablytyped
    -0.08
     BITTE
    -0.08
     ëĦ¤ìĿ´íĬ¸
    -0.07
    OrNil
    -0.07
    ieu
    -0.07
    PropertyDescriptor
    -0.07
    ym
    -0.07
    POSITIVE LOGITS
     correct
    0.07
    correct
    0.06
    amu
    0.06
    egrated
    0.05
    _correct
    0.05
    emble
    0.05
    gado
    0.05
     *
    0.05
     spacing
    0.05
    &amp
    0.05
    Activations Density 0.019%

    No Known Activations