© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 57093
    Prev
    Next
    INDEX
    Explanations

    elements related to graphical presentation or layout in documents

    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
    uild
    -0.07
    illow
    -0.07
    isu
    -0.07
    ramer
    -0.07
    uess
    -0.07
    illard
    -0.06
    loom
    -0.06
    hoa
    -0.06
    akhir
    -0.06
    og
    -0.06
    POSITIVE LOGITS
    abus
    0.08
    ward
    0.07
     feas
    0.06
    iyle
    0.06
    igned
    0.06
    èĴĤ
    0.06
    ugi
    0.06
    _ABC
    0.06
    ertino
    0.06
    Victoria
    0.06
    Activations Density 0.028%

    No Known Activations