© 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. 85942
    Prev
    Next
    INDEX
    Explanations

    titles and positions of authority or leadership

    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
    éĢļãĤĬ
    -0.08
    .histogram
    -0.07
    ameleon
    -0.07
    ensi
    -0.07
    ExecutionContext
    -0.07
    祥
    -0.07
    estate
    -0.07
    еÑĢин
    -0.07
    žit
    -0.06
    styl
    -0.06
    POSITIVE LOGITS
    utomation
    0.06
    bart
    0.06
    arks
    0.06
     Duchess
    0.06
     Sick
    0.06
     lick
    0.06
    logan
    0.06
     Borg
    0.06
    erece
    0.06
    conds
    0.06
    Activations Density 0.024%

    No Known Activations