© 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. 124329
    Prev
    Next
    INDEX
    Explanations

    numeric values that likely pertain to measurements or quantities

    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
    ëį°
    -0.11
    ORIZONTAL
    -0.07
    place
    -0.07
    ungan
    -0.07
    ait
    -0.07
    opic
    -0.07
    tte
    -0.07
    ibus
    -0.07
    ucz
    -0.07
    istic
    -0.07
    POSITIVE LOGITS
    eenth
    0.17
    een
    0.15
    ï¸ı
    0.07
    quo
    0.07
    iek
    0.07
    brtc
    0.07
    iris
    0.07
    chan
    0.07
    биÑĤ
    0.07
     Unidos
    0.07
    Activations Density 0.359%

    No Known Activations