© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 61424
    Prev
    Next
    INDEX
    Explanations

    references to mathematical properties and concepts

    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
    sein
    -0.07
    acha
    -0.07
    ienie
    -0.07
    füh
    -0.07
    ucher
    -0.07
    anke
    -0.07
    uben
    -0.06
    Neg
    -0.06
     unint
    -0.06
    addir
    -0.06
    POSITIVE LOGITS
     pylint
    0.06
    .appspot
    0.06
     Candidate
    0.06
    est
    0.06
    _trampoline
    0.05
     ëĺIJ
    0.05
    'gc
    0.05
    Candidate
    0.05
     R
    0.05
    COMMENT
    0.05
    Activations Density 0.000%

    No Known Activations