Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96309
    Prev
    Next
    INDEX
    Explanations

    financial and accounting terms related to corporate reports

    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
    eyle
    -0.07
    èª
    -0.06
     onBind
    -0.06
    hoa
    -0.06
     Mack
    -0.06
    _LL
    -0.06
     ç¸
    -0.06
     $č↵
    -0.06
    ATEGORY
    -0.06
    @student
    -0.06
    POSITIVE LOGITS
    obe
    0.07
    meli
    0.06
    getAs
    0.06
    itters
    0.06
     Klo
    0.06
     Mey
    0.06
    ktop
    0.06
    bsites
    0.06
    quire
    0.06
    Builders
    0.06
    Activations Density 0.002%

    No Known Activations