© 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. 28725
    Prev
    Next
    INDEX
    Explanations

    components related to menu structures in programming

    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
    ÑĢÑı
    -0.07
    unami
    -0.07
    olla
    -0.06
    nock
    -0.06
    iggs
    -0.06
    zept
    -0.06
    mina
    -0.06
    ÙħاÙĨ
    -0.06
    isper
    -0.06
    isd
    -0.06
    POSITIVE LOGITS
    .mainloop
    0.07
     tkinter
    0.07
    æ
    0.06
     Tcl
    0.06
     Hlav
    0.06
    xfff
    0.06
    intage
    0.06
     Tk
    0.06
    éĩįè¤ĩ
    0.06
     Beverage
    0.06
    Activations Density 0.003%

    No Known Activations