© 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. 15-LLAMASCOPE-RES-131K
    11. 27416
    Prev
    Next
    INDEX
    Explanations

    phrases related to positioning or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The phrase "front of" indicating the forward-facing side or position of objects, buildings, or areas, often used in spatial descriptions; occasionally appearing as "fronted" when used as a verb to describe facing something directly.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    jac
    -0.10
    jmu
    -0.07
    ilon
    -0.07
    xac
    -0.07
    lep
    -0.06
    ngen
    -0.06
    ÛĮÙĨÚ©
    -0.06
    inki
    -0.06
    utas
    -0.06
     waits
    -0.06
    POSITIVE LOGITS
    iers
    0.07
    -facing
    0.06
     dequeue
    0.06
    /front
    0.06
    -runner
    0.06
    front
    0.06
    (front
    0.06
     immersion
    0.06
    odka
    0.06
    ToFront
    0.06
    Activations Density 0.034%

    No Known Activations