© 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. 17-LLAMASCOPE-RES-131K
    6. 84739
    Prev
    Next
    INDEX
    Explanations

    instances of reflection and consideration about personal dilemmas or artistic struggles

    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
    agements
    -0.07
    iscard
    -0.07
    .radioButton
    -0.07
     Dich
    -0.06
    USA
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    egan
    -0.06
    dna
    -0.06
    fast
    -0.06
    .IsEmpty
    -0.06
    POSITIVE LOGITS
    SEMB
    0.07
     famously
    0.07
    é¥
    0.06
     Ladies
    0.06
     commute
    0.06
    anity
    0.06
    unsch
    0.06
    .xr
    0.06
    ansom
    0.06
    (Constructor
    0.06
    Activations Density 0.002%

    No Known Activations