© 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. 78300
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and phrases that indicate capability and flexibility in code functionality

    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
    reh
    -0.07
    uzey
    -0.07
    abcdefghijklmnop
    -0.07
    pcf
    -0.07
    WND
    -0.06
    _ENCODING
    -0.06
     Wiley
    -0.06
    abcdefghijkl
    -0.06
     ÑĤÑĢо
    -0.06
    isory
    -0.06
    POSITIVE LOGITS
     easily
    0.09
    _ATOMIC
    0.07
     Accountability
    0.07
    wang
    0.06
     without
    0.06
     later
    0.06
    apia
    0.06
     different
    0.06
     Easily
    0.06
    lish
    0.06
    Activations Density 0.048%

    No Known Activations