© 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. 88646
    Prev
    Next
    INDEX
    Explanations

    references to playful or humorous elements

    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
    adel
    -0.09
    yte
    -0.07
    arer
    -0.07
    Ð¡Ðł
    -0.07
     aks
    -0.07
    ekil
    -0.07
    žil
    -0.07
     ziy
    -0.07
    ãĥ¬ãĥĥãĥĪ
    -0.07
    urt
    -0.07
    POSITIVE LOGITS
     And
    0.08
    odos
    0.06
    enza
    0.06
    [email
    0.06
    oder
    0.06
    And
    0.06
    iá»ĥu
    0.06
    inox
    0.06
    ameda
    0.05
    oại
    0.05
    Activations Density 0.015%

    No Known Activations