© 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. 71094
    Prev
    Next
    INDEX
    Explanations

    CSS properties related to positioning and display styles

    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
    herits
    -0.08
    nonnull
    -0.08
    Interfaces
    -0.08
    BorderColor
    -0.08
    ÑģÑĤвоÑĢ
    -0.08
     پا
    -0.08
     беÑģп
    -0.07
     {.
    -0.07
    EIF
    -0.07
     esk
    -0.07
    POSITIVE LOGITS
    /by
    0.06
    .netbeans
    0.06
     floating
    0.06
     N
    0.05
    /on
    0.05
     float
    0.05
     position
    0.05
     GameController
    0.05
    ickers
    0.05
     Dell
    0.05
    Activations Density 0.002%

    No Known Activations