© 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. 3414
    Prev
    Next
    INDEX
    Explanations

    various levels of nested structures or blocks within a document

    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
    kaar
    -0.08
    =-=-=-=-=-=-=-=-
    -0.07
    ÑĢеÑĤÑĮ
    -0.07
    ÄįÃŃ
    -0.07
    ENCIES
    -0.07
    ará
    -0.07
    ÏĦÏģο
    -0.07
    deÅŁ
    -0.07
    xiety
    -0.07
    conte
    -0.07
    POSITIVE LOGITS
    yo
    0.06
    arhus
    0.06
    bservable
    0.06
     certain
    0.06
    DTV
    0.06
    astle
    0.06
    ABEL
    0.06
    gend
    0.06
    wner
    0.05
    ihu
    0.05
    Activations Density 0.085%

    No Known Activations