© 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. 55828
    Prev
    Next
    INDEX
    Explanations

    programming syntax elements related to object-oriented programming

    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
    иÑģлов
    -0.08
    ##_
    -0.07
    anki
    -0.07
    dden
    -0.07
    åı¬
    -0.07
    оÑģÑĢед
    -0.07
    urve
    -0.07
    MeasureSpec
    -0.07
    pok
    -0.07
    entai
    -0.07
    POSITIVE LOGITS
     findViewById
    0.08
    .findViewById
    0.06
    LEC
    0.06
    findViewById
    0.06
    ary
    0.05
    (gca
    0.05
     Willie
    0.05
     наÑħод
    0.05
    od
    0.05
     parallel
    0.05
    Activations Density 0.001%

    No Known Activations