© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125393
    Prev
    Next
    INDEX
    Explanations

    numeric references and identifiers associated with books

    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
     Traits
    -0.06
    esk
    -0.06
     Trait
    -0.06
    serrat
    -0.06
    bett
    -0.06
    ilda
    -0.06
    ixer
    -0.06
    ола
    -0.06
     retrospect
    -0.06
    _traits
    -0.06
    POSITIVE LOGITS
    orang
    0.07
    xies
    0.07
    -CS
    0.07
    ãģªãģĦ
    0.06
    _plugin
    0.06
    enders
    0.06
    illac
    0.06
    Ļæ±Ł
    0.06
    ctor
    0.06
     mixin
    0.06
    Activations Density 0.004%

    No Known Activations