© 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. 82854
    Prev
    Next
    INDEX
    Explanations

    the word "Our" in various contexts, indicating a focus on possessive language related to community or belonging

    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
    heads
    -0.07
    ially
    -0.06
    ams
    -0.06
    arken
    -0.06
     Lawson
    -0.06
    onic
    -0.06
    ctors
    -0.06
    ductive
    -0.06
    oc
    -0.06
    ardy
    -0.06
    POSITIVE LOGITS
    maz
    0.09
    agini
    0.08
     Own
    0.07
    vod
    0.07
    imary
    0.07
    krom
    0.07
    êu
    0.07
    tesy
    0.07
    RIPT
    0.07
    Vue
    0.07
    Activations Density 0.016%

    No Known Activations