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. 17-LLAMASCOPE-RES-131K
    6. 76523
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly in the context of data manipulation

    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
     Liver
    -0.07
    hone
    -0.07
    igham
    -0.06
    ilan
    -0.06
     PhpStorm
    -0.06
    elps
    -0.06
    eric
    -0.06
     forget
    -0.06
    adele
    -0.06
    ç´ł
    -0.06
    POSITIVE LOGITS
    ::*
    0.07
    .Guna
    0.07
     Bash
    0.06
    Microsoft
    0.06
    DK
    0.06
     hashtable
    0.06
     seper
    0.06
    .enum
    0.06
    baseline
    0.06
    wil
    0.06
    Activations Density 0.013%

    No Known Activations