© 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. 29240
    Prev
    Next
    INDEX
    Explanations

    occurrences of cooking instructions and process-related phrases

    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
    ople
    -0.08
    anova
    -0.08
    ograd
    -0.07
    ÑĢÑıдÑĥ
    -0.07
    StackSize
    -0.07
    _tot
    -0.07
    LETE
    -0.07
    avirus
    -0.07
     behalf
    -0.07
    etti
    -0.07
    POSITIVE LOGITS
    309
    0.07
     meanwhile
    0.07
     Oliv
    0.06
    ToProps
    0.06
     же
    0.06
    ÏĮÏĦε
    0.06
    ainer
    0.06
    .ops
    0.06
     Hed
    0.06
    endi
    0.06
    Activations Density 0.005%

    No Known Activations