© 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. 15-LLAMASCOPE-RES-131K
    11. 103927
    Prev
    Next
    INDEX
    Explanations

    references to real estate developments and their details

    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
    ahir
    -0.07
     Wallace
    -0.06
    ách
    -0.06
    ISTR
    -0.06
    OutOf
    -0.06
    bourne
    -0.06
     Barnes
    -0.06
    ervo
    -0.06
    ustos
    -0.06
    ouve
    -0.06
    POSITIVE LOGITS
     rodin
    0.07
    hod
    0.07
    acyj
    0.07
     floor
    0.07
    edata
    0.06
    agal
    0.06
    -overlay
    0.06
    ое
    0.06
    ogn
    0.06
     _|
    0.06
    Activations Density 0.006%

    No Known Activations