© 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. 73664
    Prev
    Next
    INDEX
    Explanations

    formal political references and related actions

    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
    æĭ¥
    -0.07
     sadd
    -0.07
    ãĨ
    -0.07
    âĸį
    -0.07
    080
    -0.07
    vale
    -0.07
    âĦĸâĦĸ
    -0.07
    .ctrl
    -0.07
    rf
    -0.06
    phinx
    -0.06
    POSITIVE LOGITS
    dorf
    0.08
     Wilkinson
    0.06
    ©
    0.06
    alker
    0.06
    fila
    0.06
    f
    0.06
    uns
    0.06
    izador
    0.06
    i
    0.05
    fra
    0.05
    Activations Density 0.020%

    No Known Activations