© 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. 17-LLAMASCOPE-RES-131K
    11. 16524
    Prev
    Next
    INDEX
    Explanations

    titles and roles of leadership positions

    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
    changer
    -0.07
    jang
    -0.07
    Overrides
    -0.07
    aler
    -0.07
    ALER
    -0.07
    ulo
    -0.06
    aca
    -0.06
    osexual
    -0.06
    genes
    -0.06
    _dispatch
    -0.06
    POSITIVE LOGITS
     operating
    0.07
    lain
    0.06
    ikler
    0.06
     Operating
    0.06
    tec
    0.06
     lifelong
    0.06
    STRU
    0.05
     Rav
    0.05
     dipl
    0.05
     آپ
    0.05
    Activations Density 0.005%

    No Known Activations