© 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. 16144
    Prev
    Next
    INDEX
    Explanations

    concepts related to existence and identity across different philosophical 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
    phant
    -0.07
    å®Ļ
    -0.07
    Ø´Ùĩ
    -0.06
    hir
    -0.06
     اÙĦØ·
    -0.06
    rost
    -0.06
    mür
    -0.06
    _gs
    -0.06
    اعÙĬ
    -0.06
    -bs
    -0.06
    POSITIVE LOGITS
     Relevant
    0.07
    ieten
    0.07
    shima
    0.07
     relevant
    0.07
    otta
    0.07
     Crud
    0.07
    relevant
    0.06
    oyo
    0.06
     everything
    0.06
     Williamson
    0.06
    Activations Density 0.001%

    No Known Activations