© 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. 17-LLAMASCOPE-RES-131K
    6. 118406
    Prev
    Next
    INDEX
    Explanations

    phrases related to decision-making and choice

    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
    инкÑĥ
    -0.06
    ÌĨ
    -0.06
    ноз
    -0.06
    bis
    -0.06
    riba
    -0.06
    Ñĸон
    -0.06
    Coeff
    -0.06
    .Enums
    -0.06
    ä¸įäºĨ
    -0.06
    åĬĽçļĦ
    -0.06
    POSITIVE LOGITS
    alla
    0.07
    resi
    0.07
    /opt
    0.06
    ighb
    0.06
    ovice
    0.06
    å°ĸ
    0.06
     Opt
    0.06
     AsyncCallback
    0.06
    emd
    0.06
    InSection
    0.06
    Activations Density 0.002%

    No Known Activations