© 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. 9-LLAMASCOPE-RES-131K
    11. 98658
    Prev
    Next
    INDEX
    Explanations

    occurrences of dashes or hyphens, typically used in formatting or indicating breaks 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
    zew
    -0.07
    enek
    -0.06
    abouts
    -0.06
    .SDK
    -0.06
    ercul
    -0.06
    ei
    -0.06
    istine
    -0.06
    ighted
    -0.06
    .ns
    -0.06
    ricula
    -0.06
    POSITIVE LOGITS
    udu
    0.07
    ÙĪجÙĩ
    0.06
    .getDrawable
    0.06
    ä¸Ī
    0.06
    orem
    0.06
     yup
    0.06
    رة
    0.06
    kest
    0.06
     Faith
    0.06
    aviours
    0.06
    Activations Density 0.001%

    No Known Activations