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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 125603
    Prev
    Next
    INDEX
    Explanations

    words related to categorization and classification

    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
    ially
    -0.07
    oog
    -0.06
    ALLY
    -0.06
    ayan
    -0.05
    omorphic
    -0.05
     gas
    -0.05
     che
    -0.05
    branch
    -0.05
     kh
    -0.05
     gymn
    -0.05
    POSITIVE LOGITS
    kening
    0.08
    ØŃات
    0.08
    imento
    0.07
    Ñĩив
    0.07
     Loose
    0.07
    inkel
    0.07
    ecast
    0.07
    ingen
    0.07
    kan
    0.07
    ulong
    0.07
    Activations Density 0.043%

    No Known Activations