© 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. 125577
    Prev
    Next
    INDEX
    Explanations

    key details related to business-related developments and statistics

    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
    ibri
    -0.07
    jišť
    -0.06
    ngr
    -0.06
     Boeing
    -0.06
    rique
    -0.06
    iswa
    -0.06
    iya
    -0.06
    berger
    -0.06
     taper
    -0.06
     cocaine
    -0.06
    POSITIVE LOGITS
     models
    0.07
     urban
    0.07
    Models
    0.07
    ÙĦÙĪد
    0.07
     Models
    0.06
    Auto
    0.06
    models
    0.06
    तर
    0.06
     brand
    0.06
    stract
    0.06
    Activations Density 0.000%

    No Known Activations