© 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. 119434
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions and corporations

    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
    asha
    -0.07
    arah
    -0.07
    elda
    -0.06
    ÅĻeh
    -0.06
    ouz
    -0.06
    alla
    -0.06
    iez
    -0.06
    ILLA
    -0.06
    sequential
    -0.06
    aec
    -0.06
    POSITIVE LOGITS
     Bank
    0.09
     bank
    0.09
    ruptcy
    0.08
     Chase
    0.07
     Vect
    0.07
    éĬĢè¡Į
    0.07
     BANK
    0.07
    .bank
    0.07
    ãģįãģŁ
    0.07
    Æ°á»Ľng
    0.07
    Activations Density 0.016%

    No Known Activations