© 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. 15-LLAMASCOPE-RES-131K
    11. 88347
    Prev
    Next
    INDEX
    Explanations

    statistical terms and numerical data within a document

    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
    asca
    -0.07
    shaw
    -0.06
    oby
    -0.06
    ÏĦÏħ
    -0.06
    даÑĤ
    -0.06
     бÑĢа
    -0.06
    .leave
    -0.06
     Gordon
    -0.06
    ceph
    -0.06
    наÑĤ
    -0.06
    POSITIVE LOGITS
    thenReturn
    0.07
    ków
    0.06
    URRE
    0.06
     Gil
    0.06
    azione
    0.06
    ÙĬÙĨØ©
    0.06
     UnityEditor
    0.06
    getManager
    0.06
    occo
    0.06
    codile
    0.06
    Activations Density 0.055%

    No Known Activations