© 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. 27263
    Prev
    Next
    INDEX
    Explanations

    the word "some" in various contexts

    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
    swer
    -0.08
    uers
    -0.08
     someone
    -0.07
    ãĥªãĥ¼ãĤº
    -0.07
    اتÛĮ
    -0.07
    edm
    -0.07
    aal
    -0.07
    ÄĽtÅ¡
    -0.07
     something
    -0.07
    اÙĨÙĩ
    -0.07
    POSITIVE LOGITS
    ones
    0.16
    /all
    0.16
    place
    0.15
    kind
    0.11
    ht
    0.10
     of
    0.10
    hw
    0.10
    obody
    0.10
    -times
    0.10
    ONES
    0.10
    Activations Density 0.092%

    No Known Activations