© 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. 125667
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols used in text

    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
    üstü
    -0.07
    ounder
    -0.07
    unner
    -0.06
    ffen
    -0.06
     vet
    -0.06
    clist
    -0.06
     mojo
    -0.06
     гÑĢÑĥ
    -0.06
     grunt
    -0.06
    lobe
    -0.06
    POSITIVE LOGITS
    SSID
    0.07
    sez
    0.06
    ucci
    0.06
    eus
    0.06
    ANDING
    0.06
     acc
    0.06
    SSH
    0.06
    achel
    0.06
    otine
    0.06
    WindowTitle
    0.06
    Activations Density 0.010%

    No Known Activations