© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 73718
    Prev
    Next
    INDEX
    Explanations

    action verbs related to engagement and interaction

    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
    asma
    -0.06
    ltra
    -0.06
    utf
    -0.06
     kariy
    -0.06
    inal
    -0.06
    iom
    -0.06
    ÙĪارÙĩ
    -0.06
    mented
    -0.06
    stit
    -0.06
    orrent
    -0.06
    POSITIVE LOGITS
    çĬ
    0.07
    defs
    0.07
    Field
    0.06
    ONA
    0.06
    ona
    0.06
     soud
    0.06
    swagger
    0.06
     jedn
    0.06
     Field
    0.06
    nez
    0.06
    Activations Density 0.032%

    No Known Activations