© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 39928
    Prev
    Next
    INDEX
    Explanations

    phrases indicating experience or involvement in activities

    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
    лоÑĢ
    -0.07
    boom
    -0.07
    èm
    -0.07
    мени
    -0.07
    ific
    -0.06
    ấn
    -0.06
    inaire
    -0.06
    еÑĢаÑĤÑĥ
    -0.06
     Apprent
    -0.06
    UIT
    -0.06
    POSITIVE LOGITS
    byt
    0.07
     prev
    0.06
    ardon
    0.06
    amil
    0.06
    zy
    0.06
    ASTE
    0.06
    aste
    0.06
     cyl
    0.06
    32
    0.06
    avel
    0.06
    Activations Density 0.018%

    No Known Activations