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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96175
    Prev
    Next
    INDEX
    Explanations

    final keywords in programming or software-related contexts

    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
    lington
    -0.07
    iju
    -0.07
     å¾
    -0.06
    cho
    -0.06
    нев
    -0.06
    lij
    -0.06
    ught
    -0.06
    pery
    -0.06
    antu
    -0.06
    emic
    -0.06
    POSITIVE LOGITS
    CDC
    0.06
    ´Ģ
    0.06
    RW
    0.06
    TZ
    0.06
    iggins
    0.06
    ieder
    0.06
    콩
    0.06
    ινÏĮ
    0.06
    ardo
    0.06
    ,strlen
    0.06
    Activations Density 0.002%

    No Known Activations