© 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. 15-LLAMASCOPE-RES-131K
    11. 88108
    Prev
    Next
    INDEX
    Explanations

    navigational elements and structure in web-related content

    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
    AndGet
    -0.09
    nger
    -0.08
    WEBPACK
    -0.06
    acio
    -0.06
    .gdx
    -0.06
    antiago
    -0.06
    ÐĤ
    -0.06
    -icons
    -0.06
    entina
    -0.06
    ChangedEventArgs
    -0.06
    POSITIVE LOGITS
    icher
    0.07
    mma
    0.06
     Foam
    0.06
    imiter
    0.06
     Sandwich
    0.06
    Ñĥка
    0.06
    è¶
    0.06
    ãĥĦ
    0.06
     dün
    0.06
    _sidebar
    0.06
    Activations Density 0.005%

    No Known Activations