© 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. 60930
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "approve."

    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
    rupa
    -0.06
    å¨
    -0.06
     ration
    -0.06
    ller
    -0.06
     wellness
    -0.06
    .nih
    -0.06
    Ãłnh
    -0.06
    mini
    -0.06
     addCriterion
    -0.06
    (())↵
    -0.06
    POSITIVE LOGITS
    IGNAL
    0.07
    ASSES
    0.06
    gin
    0.06
    138
    0.06
    DataMember
    0.06
     probe
    0.06
     Ventura
    0.06
    folio
    0.06
    476
    0.06
     faculties
    0.06
    Activations Density 0.040%

    No Known Activations