© 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. 72728
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to software development and testing processes

    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
    ttp
    -0.07
    -urlencoded
    -0.07
    aign
    -0.07
    RTOS
    -0.07
    lse
    -0.07
    оди
    -0.06
    umbn
    -0.06
    ASET
    -0.06
    /dat
    -0.06
    boa
    -0.06
    POSITIVE LOGITS
    :
    0.06
    .UNKNOWN
    0.06
    mouseenter
    0.06
    ÑĢÑĥж
    0.06
    cade
    0.06
     görev
    0.06
    .SQLite
    0.06
    461
    0.05
    輪
    0.05
    /-
    0.05
    Activations Density 0.029%

    No Known Activations