© 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. 15-LLAMASCOPE-RES-131K
    11. 88883
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural or historical groups, particularly related to the Samaritan and Jewish communities

    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
    è¸ı
    -0.07
    uu
    -0.07
     sav
    -0.07
    Statics
    -0.06
    anding
    -0.06
     aks
    -0.06
    assic
    -0.06
     Savage
    -0.06
    894
    -0.06
    ORMAT
    -0.06
    POSITIVE LOGITS
    .DefaultCellStyle
    0.07
     horizon
    0.07
    uder
    0.07
    ÑģÑĤÑĢой
    0.07
    unya
    0.07
     gloss
    0.06
     Joanna
    0.06
    aklı
    0.06
    pur
    0.06
    åī£
    0.06
    Activations Density 0.002%

    No Known Activations