© 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. 75011
    Prev
    Next
    INDEX
    Explanations

    instances of "of" 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
    каж
    -0.07
    lero
    -0.07
    ago
    -0.07
    elters
    -0.07
    วà¸Ļ
    -0.06
    otal
    -0.06
    μον
    -0.06
    ким
    -0.06
     Equip
    -0.06
    kip
    -0.06
    POSITIVE LOGITS
     sorts
    0.13
     eins
    0.07
    course
    0.07
     course
    0.07
    icina
    0.07
    icers
    0.07
     sort
    0.07
     various
    0.07
    sort
    0.06
    SORT
    0.06
    Activations Density 0.017%

    No Known Activations