© 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. 5-LLAMASCOPE-RES-131K
    6. 125433
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of recoil in firearms and physics

    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
    uslim
    -0.07
    ily
    -0.06
    vvm
    -0.06
    DET
    -0.06
    590
    -0.06
    iral
    -0.06
    à¸Ļำ
    -0.06
    ropping
    -0.06
    es
    -0.05
     till
    -0.05
    POSITIVE LOGITS
    ARRIER
    0.07
    ado
    0.07
    asse
    0.07
    adro
    0.07
    .charset
    0.07
    uter
    0.07
    ux
    0.07
    beck
    0.06
    felt
    0.06
    pees
    0.06
    Activations Density 0.001%

    No Known Activations