© 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. 17-LLAMASCOPE-RES-131K
    11. 94340
    Prev
    Next
    INDEX
    Explanations

    phrases associated with user authentication and validation logic

    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
    ÑĢев
    -0.07
    robe
    -0.06
    жа
    -0.06
    435
    -0.06
    ehir
    -0.06
     Lup
    -0.06
    зи
    -0.06
    82
    -0.06
    kt
    -0.06
     Liter
    -0.06
    POSITIVE LOGITS
    jal
    0.07
    AndView
    0.07
    iri
    0.06
    ãĥĮ
    0.06
    peg
    0.06
     Crown
    0.06
     Bender
    0.06
    ppv
    0.06
     corp
    0.06
     度
    0.06
    Activations Density 0.007%

    No Known Activations