© 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 EvalsExportsinterp-engineNEWAPI 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. 28088
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "details" in various contexts, indicating a focus on the presence of specific information or supplementary content

    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
    fare
    -0.07
    èn
    -0.06
    regar
    -0.06
    èm
    -0.06
     Said
    -0.06
    oha
    -0.06
    eding
    -0.06
    ucha
    -0.06
     Thermal
    -0.06
    erer
    -0.06
    POSITIVE LOGITS
     kaf
    0.07
    ãĥ¼ãĥĦ
    0.07
    OMPI
    0.07
    uff
    0.06
    ERING
    0.06
    ä¸ĢåĮº
    0.06
    ¢åįķ
    0.06
    PD
    0.06
     Dough
    0.06
    laps
    0.06
    Activations Density 0.003%

    No Known Activations