© 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. 88683
    Prev
    Next
    INDEX
    Explanations

    expressions of personal activities and creative processes

    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
    Ãły
    -0.07
    father
    -0.07
    irq
    -0.07
    _numer
    -0.07
    ç¦ıåĪ©
    -0.07
    defgroup
    -0.06
    ydı
    -0.06
    uese
    -0.06
    uft
    -0.06
    ambil
    -0.06
    POSITIVE LOGITS
    ohana
    0.07
    illac
    0.07
     lately
    0.06
    640
    0.06
    doch
    0.06
    ãĥĭãĤ¢
    0.06
     husband
    0.06
    fer
    0.06
     thai
    0.06
     Kund
    0.05
    Activations Density 0.025%

    No Known Activations