© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 86283
    Prev
    Next
    INDEX
    Explanations

    elements related to financial transactions and obligations

    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
     SUBSTITUTE
    -0.09
    ãĥ¼ãĥį
    -0.08
     migrationBuilder
    -0.07
    rieb
    -0.07
    ué
    -0.07
    ãģ¹ãģį
    -0.07
    .mybatisplus
    -0.07
    Ñģол
    -0.07
    ebek
    -0.07
    ÑĨенÑĤÑĢа
    -0.07
    POSITIVE LOGITS
     allow
    0.12
     granting
    0.11
     allowing
    0.11
     Allow
    0.11
    allow
    0.10
     allows
    0.10
    Allow
    0.10
     allowance
    0.10
     generosity
    0.10
     mercy
    0.10
    Activations Density 0.038%

    No Known Activations