© 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. 9-LLAMASCOPE-RES-131K
    6. 95473
    Prev
    Next
    INDEX
    Explanations

    terms and keywords related to Apache Spark and its functionalities

    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
    oret
    -0.08
    eries
    -0.07
    atabases
    -0.06
    ora
    -0.06
    ius
    -0.06
    cone
    -0.06
    oya
    -0.06
    ighthouse
    -0.06
    olumn
    -0.06
    ansi
    -0.06
    POSITIVE LOGITS
    HeaderValue
    0.07
    (IL
    0.07
    ëĭ´
    0.07
    ÄIJT
    0.06
    aar
    0.06
    \views
    0.06
    NCY
    0.06
    seed
    0.06
    Seed
    0.06
    _rl
    0.06
    Activations Density 0.001%

    No Known Activations