Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 126212
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and structure

    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
    MLE
    -0.08
    -pdf
    -0.07
    STRU
    -0.07
    stru
    -0.07
    irie
    -0.06
    رÙĬÙĥ
    -0.06
    ounc
    -0.06
    /views
    -0.06
    elib
    -0.06
    .synthetic
    -0.06
    POSITIVE LOGITS
    oton
    0.06
    ráf
    0.06
    rases
    0.06
    аÑĤо
    0.06
    kke
    0.06
     Ion
    0.06
    تا
    0.06
     Doyle
    0.06
     container
    0.06
    Untitled
    0.06
    Activations Density 0.005%

    No Known Activations