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

    Neuronpedia

    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. 26692
    Prev
    Next
    INDEX
    Explanations

    references to physical postal addresses or boxes

    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
    869
    -0.07
    inges
    -0.07
    918
    -0.06
    asco
    -0.06
    зв
    -0.06
    gency
    -0.06
    amac
    -0.06
    526
    -0.06
    inois
    -0.06
    subtotal
    -0.06
    POSITIVE LOGITS
    Äįer
    0.08
    [sizeof
    0.07
    RTL
    0.07
     JNI
    0.07
    اÙĪ
    0.06
     Bearings
    0.06
    taj
    0.06
    .GUI
    0.06
     Operand
    0.06
    ao
    0.06
    Activations Density 0.002%

    No Known Activations