© 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. 75230
    Prev
    Next
    INDEX
    Explanations

    articles, especially "the," and references related to various subjects

    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
    stroy
    -0.07
    arah
    -0.07
    aru
    -0.07
    atee
    -0.06
    neau
    -0.06
    à¤ľà¤°
    -0.06
    溶
    -0.06
    apers
    -0.06
    ارس
    -0.06
    elenium
    -0.06
    POSITIVE LOGITS
     thereof
    0.07
    oret
    0.07
    tring
    0.07
    ocracy
    0.06
    404
    0.06
     ilk
    0.06
    ÑĤим
    0.06
    ught
    0.06
     mere
    0.06
    tiv
    0.06
    Activations Density 0.013%

    No Known Activations