© 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. 105627
    Prev
    Next
    INDEX
    Explanations

    references to college admissions and educational programs

    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
    lac
    -0.07
    acas
    -0.07
     lac
    -0.06
    asaki
    -0.06
    iones
    -0.06
     faculty
    -0.06
     Immutable
    -0.05
     dissoci
    -0.05
    μÎŃ
    -0.05
    quet
    -0.05
    POSITIVE LOGITS
     programs
    0.09
     Programs
    0.08
     programas
    0.08
    opup
    0.07
    programs
    0.07
     programmes
    0.07
    ivate
    0.07
    ìĿ´íģ¬
    0.07
    into
    0.07
    gewater
    0.07
    Activations Density 0.010%

    No Known Activations