© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87709
    Prev
    Next
    INDEX
    Explanations

    programming and library function calls commonly associated with Python development

    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
    ystate
    -0.08
    lew
    -0.06
    aeda
    -0.06
    ewis
    -0.06
    blem
    -0.06
    history
    -0.06
    aroo
    -0.06
    seau
    -0.06
    ius
    -0.06
    OOK
    -0.06
    POSITIVE LOGITS
     conv
    0.06
    CPF
    0.06
    ÏĦικα
    0.06
     Mitar
    0.06
    assin
    0.06
    ائÙĦ
    0.06
    _transition
    0.06
    clusive
    0.06
    ãĥ©ãĤ¹
    0.05
    rafted
    0.05
    Activations Density 0.000%

    No Known Activations