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. 22-LLAMASCOPE-RES-131K
    6. 5260
    Prev
    Next
    INDEX
    Explanations

    HTML and web-related access key attributes

    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
    agara
    -0.07
     Kag
    -0.06
    ihan
    -0.06
    çķª
    -0.06
    tein
    -0.06
    rish
    -0.05
    odal
    -0.05
    wn
    -0.05
     Occupy
    -0.05
    idal
    -0.05
    POSITIVE LOGITS
    -duty
    0.08
     Duty
    0.08
     NÄĽm
    0.07
    /xhtml
    0.07
     duty
    0.07
    _PIX
    0.07
    ÏĥÏĦο
    0.07
     Readonly
    0.07
     Snape
    0.07
     QImage
    0.07
    Activations Density 0.001%

    No Known Activations