© 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. 28879
    Prev
    Next
    INDEX
    Explanations

    phrases that express challenge or difficulty

    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
     Verfügung
    -0.07
    elle
    -0.06
    oit
    -0.06
    Ì
    -0.06
    _traits
    -0.06
    _ORIGIN
    -0.06
    ÙĪØ´
    -0.06
     Howell
    -0.06
    lias
    -0.06
     tactical
    -0.05
    POSITIVE LOGITS
     balancing
    0.07
    ingleton
    0.07
    abal
    0.07
    angi
    0.07
     вообÑīе
    0.07
    ingo
    0.07
    ocrat
    0.07
     balance
    0.07
    zell
    0.07
    Balance
    0.06
    Activations Density 0.040%

    No Known Activations