© 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. 2367
    Prev
    Next
    INDEX
    Explanations

    words related to personal names and locations, especially those with a specific pattern in spelling

    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
     waktu
    -0.07
     odp
    -0.07
    éric
    -0.07
    hz
    -0.07
    uten
    -0.07
    stav
    -0.07
    waves
    -0.07
    ãģįãģŁ
    -0.07
    udas
    -0.07
    yms
    -0.07
    POSITIVE LOGITS
    onder
    0.07
    arrant
    0.07
    avelength
    0.07
    arrants
    0.06
    ngth
    0.06
    heels
    0.06
    chester
    0.06
    reck
    0.06
    ãĥ¥
    0.06
     lá»ħ
    0.06
    Activations Density 0.078%

    No Known Activations