© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106849
    Prev
    Next
    INDEX
    Explanations

    words related to affordability or low prices

    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
    artz
    -0.07
    olit
    -0.07
    awi
    -0.07
    iate
    -0.06
    Inspectable
    -0.06
    ncia
    -0.06
    ingly
    -0.06
    ardy
    -0.06
    arde
    -0.06
    inki
    -0.06
    POSITIVE LOGITS
     Cul
    0.07
     cul
    0.06
    [section
    0.06
    elerik
    0.06
    imiter
    0.06
    izedName
    0.06
     Kho
    0.06
     ele
    0.06
    cul
    0.06
    rita
    0.06
    Activations Density 0.000%

    No Known Activations