© 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 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. 17-LLAMASCOPE-RES-131K
    11. 93772
    Prev
    Next
    INDEX
    Explanations

    keywords related to wallpapers and background images for devices

    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
     guest
    -0.07
     Anch
    -0.07
    Assembly
    -0.06
     Guest
    -0.06
    é¾Ħ
    -0.06
     Universe
    -0.06
    زب
    -0.06
     deliberate
    -0.06
    vale
    -0.06
    guest
    -0.06
    POSITIVE LOGITS
    :CGRect
    0.07
    rig
    0.07
    DDD
    0.06
    ysi
    0.06
    .typ
    0.06
    rl
    0.06
    ru
    0.06
    аÑĢÑĩ
    0.06
    lags
    0.06
    erus
    0.06
    Activations Density 0.002%

    No Known Activations