© 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. 78650
    Prev
    Next
    INDEX
    Explanations

    references to postal codes or ZIP codes

    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
    ardin
    -0.07
    ennen
    -0.07
    è²Ŀ
    -0.07
    ابت
    -0.07
     fri
    -0.07
    iÄĻ
    -0.07
    adium
    -0.06
    >Returns
    -0.06
    gaard
    -0.06
    ief
    -0.06
    POSITIVE LOGITS
    sob
    0.07
     Gib
    0.06
    s
    0.06
    code
    0.06
    _claim
    0.06
    æĺŃ
    0.06
    ÑĨин
    0.06
    ansas
    0.06
     humili
    0.06
     Gibbs
    0.06
    Activations Density 0.000%

    No Known Activations