© 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. 58456
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific Swedish characters or sequences that could indicate numbered or quantified items

    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
    414
    -0.08
    ales
    -0.07
    Ỽ
    -0.07
    arness
    -0.07
    ķĮ
    -0.06
    ocha
    -0.06
    _PIPE
    -0.06
    keit
    -0.06
    pered
    -0.06
     Ale
    -0.06
    POSITIVE LOGITS
    ovich
    0.06
    gaard
    0.06
     hei
    0.06
    777
    0.06
    ationally
    0.06
    foy
    0.06
     Guru
    0.05
    ارÛĮØ®
    0.05
    eterangan
    0.05
    387
    0.05
    Activations Density 0.000%

    No Known Activations