© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61660
    Prev
    Next
    INDEX
    Explanations

    instances of holding positions or qualifications

    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
    479
    -0.07
    224
    -0.07
    409
    -0.06
    jev
    -0.06
    eut
    -0.06
    оÑĢи
    -0.06
    unes
    -0.06
    kte
    -0.06
    ez
    -0.06
    ole
    -0.06
    POSITIVE LOGITS
    ziel
    0.07
    bart
    0.07
    erb
    0.07
     Lonely
    0.06
    ç½
    0.06
     sway
    0.06
    NING
    0.06
    алÑĭ
    0.06
     Burton
    0.06
     Ire
    0.06
    Activations Density 0.010%

    No Known Activations