Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95936
    Prev
    Next
    INDEX
    Explanations

    elements related to UI components and their attributes in a programming context

    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
     Maar
    -0.07
    åĽº
    -0.07
    iek
    -0.06
    phia
    -0.06
     Hughes
    -0.06
     Goldberg
    -0.06
    vecs
    -0.06
    oso
    -0.06
    quate
    -0.06
    cle
    -0.06
    POSITIVE LOGITS
    ogy
    0.08
    èģĶç½ij
    0.07
    -alist
    0.07
    ftype
    0.06
    CCR
    0.06
    461
    0.06
    Radians
    0.06
    undi
    0.06
    çon
    0.06
    ÑĢаÑģ
    0.06
    Activations Density 0.005%

    No Known Activations