© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 94717
    Prev
    Next
    INDEX
    Explanations

    references to pulse-width modulation (PWM) in code

    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
    igm
    -0.08
    axy
    -0.07
    reak
    -0.07
    евид
    -0.07
    ysz
    -0.07
    .scalablytyped
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    bib
    -0.07
    ngrx
    -0.07
    ermo
    -0.07
    POSITIVE LOGITS
    rd
    0.07
    ening
    0.06
    able
    0.06
     Harbor
    0.06
     Rams
    0.06
    arts
    0.06
     Pere
    0.06
    down
    0.06
    dw
    0.06
    storm
    0.06
    Activations Density 0.002%

    No Known Activations