© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3748
    Prev
    Next
    INDEX
    Explanations

    names of people, particularly those associated with notable accomplishments or roles

    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
    .TestTools
    -0.08
    _DP
    -0.08
       
    -0.08
    ëħ¸ì¶ľ
    -0.08
    ëģĶ
    -0.08
     lượng
    -0.08
    uai
    -0.07
    mate
    -0.07
    Ìĥ
    -0.07
    /player
    -0.07
    POSITIVE LOGITS
    son
    0.09
    sson
    0.08
    ately
    0.07
     latter
    0.07
    /or
    0.07
    naire
    0.07
    thal
    0.07
    ity
    0.06
    ously
    0.06
    cence
    0.06
    Activations Density 0.034%

    No Known Activations