© 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. 56320
    Prev
    Next
    INDEX
    Explanations

    phrases related to limitations and structured programs

    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
    unks
    -0.06
    adia
    -0.06
     stuff
    -0.06
    cake
    -0.05
    ÃŁe
    -0.05
    ãĥ¼ãĤº
    -0.05
    _traits
    -0.05
     now
    -0.05
     Oct
    -0.05
     latter
    -0.05
    POSITIVE LOGITS
    kup
    0.07
     Kür
    0.07
     subtotal
    0.07
    _MUTEX
    0.07
    isclosed
    0.07
    ÏįÏĦε
    0.07
    .zh
    0.07
    å¼ĺ
    0.07
     Weekly
    0.07
    ptest
    0.07
    Activations Density 0.000%

    No Known Activations