© 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. 15-LLAMASCOPE-RES-131K
    11. 104088
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to data handling and processing

    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
    edList
    -0.06
    acho
    -0.05
    -ticket
    -0.05
     spl
    -0.05
     Kush
    -0.05
    pos
    -0.05
    occo
    -0.05
    urve
    -0.05
    iais
    -0.05
    cre
    -0.05
    POSITIVE LOGITS
    å¦Ĥä¸ĭ
    0.08
     ç«ĭ
    0.07
    PEnd
    0.07
    æŁĦ
    0.07
    ÙĩاÛĮÛĮ
    0.07
    سطس
    0.07
    Streams
    0.07
    gst
    0.07
    klady
    0.07
    ör
    0.07
    Activations Density 0.062%

    No Known Activations