© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 62466
    Prev
    Next
    INDEX
    Explanations

    modal verbs indicating obligation or necessity

    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
     Kab
    -0.06
    áš
    -0.06
    Ĵ
    -0.06
    roperty
    -0.06
    ÑĢÑĥп
    -0.06
    assy
    -0.06
    hs
    -0.06
    pb
    -0.06
     Abbott
    -0.06
    hdl
    -0.06
    POSITIVE LOGITS
     be
    0.09
    ajas
    0.08
    turnstile
    0.07
    ienda
    0.07
    odule
    0.07
    aland
    0.06
    .DataVisualization
    0.06
    ods
    0.06
    chu
    0.06
     بتÙĪاÙĨ
    0.06
    Activations Density 0.030%

    No Known Activations