© 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. 79269
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "being part of" or "belonging to" a group or category

    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
    %E
    -0.08
    oyer
    -0.07
    astle
    -0.07
    olet
    -0.07
    iership
    -0.07
    ookies
    -0.07
     Colbert
    -0.06
    chk
    -0.06
    xing
    -0.06
    irit
    -0.06
    POSITIVE LOGITS
     Meng
    0.07
    isnan
    0.06
    lico
    0.06
     Budd
    0.06
     among
    0.06
     Opposition
    0.06
     von
    0.06
     bana
    0.06
    mgr
    0.06
     بس
    0.06
    Activations Density 0.031%

    No Known Activations