© 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. 123693
    Prev
    Next
    INDEX
    Explanations

    phrases related to making choices or selections

    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
    мена
    -0.07
    nz
    -0.06
    ntax
    -0.06
    glas
    -0.06
     import
    -0.06
    phies
    -0.06
    ÙĥÙĩ
    -0.06
    cken
    -0.06
    isti
    -0.06
     cigaret
    -0.06
    POSITIVE LOGITS
     locations
    0.15
     location
    0.15
     Locations
    0.13
    locations
    0.13
     cities
    0.12
    location
    0.11
     located
    0.11
     Location
    0.11
    Locations
    0.11
    -location
    0.11
    Activations Density 0.033%

    No Known Activations