© 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. 9-LLAMASCOPE-RES-131K
    6. 95915
    Prev
    Next
    INDEX
    Explanations

    references to player substitutions and changes in positions during a sports match

    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
    inux
    -0.07
    ByExample
    -0.07
    ItemSelectedListener
    -0.07
    ritel
    -0.07
    _inf
    -0.07
    woord
    -0.07
    udge
    -0.07
    hower
    -0.06
    -fill
    -0.06
    phia
    -0.06
    POSITIVE LOGITS
    AtA
    0.07
     conv
    0.06
     Doub
    0.06
    anlar
    0.06
     Bett
    0.06
     win
    0.06
    ested
    0.06
     Fur
    0.05
     convo
    0.05
     cant
    0.05
    Activations Density 0.002%

    No Known Activations