© 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. 60687
    Prev
    Next
    INDEX
    Explanations

    details about retail establishments and commercial spaces

    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
    BoxLayout
    -0.08
    istrov
    -0.06
    sth
    -0.06
    sj
    -0.06
    geber
    -0.06
    acd
    -0.06
    ordova
    -0.06
    ák
    -0.06
    iedo
    -0.06
    QN
    -0.06
    POSITIVE LOGITS
    ücü
    0.06
    ocs
    0.06
    -office
    0.06
    /browse
    0.06
    outers
    0.06
    สำà¸Ļ
    0.06
     Benn
    0.06
    enso
    0.06
     Merlin
    0.06
    __.
    0.06
    Activations Density 0.007%

    No Known Activations