© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 84057
    Prev
    Next
    INDEX
    Explanations

    references to popular car models and their attributes

    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
    .scalablytyped
    -0.08
    ÙĪرش
    -0.07
    ÂIJ
    -0.07
    Ùĩد
    -0.07
     ucfirst
    -0.07
    statt
    -0.06
    memberof
    -0.06
     ãĢ
    -0.06
    .WriteAll
    -0.06
    _BEGIN
    -0.06
    POSITIVE LOGITS
     the
    0.09
     models
    0.08
     The
    0.07
    hei
    0.07
    models
    0.07
    vara
    0.07
    ,the
    0.07
     model
    0.07
     Models
    0.06
     modelo
    0.06
    Activations Density 0.030%

    No Known Activations