© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3706
    Prev
    Next
    INDEX
    Explanations

    references to Wikipedia and its associated content

    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
    blr
    -0.06
    ikan
    -0.06
    otten
    -0.06
     du
    -0.06
    -mount
    -0.05
     mount
    -0.05
    appa
    -0.05
    affer
    -0.05
     cent
    -0.05
    ostat
    -0.05
    POSITIVE LOGITS
    HN
    0.07
    arda
    0.07
    zag
    0.07
    ë¿IJ
    0.07
    buch
    0.07
    $LANG
    0.07
    isclosed
    0.06
     decltype
    0.06
    ograd
    0.06
    /Dk
    0.06
    Activations Density 0.001%

    No Known Activations