© 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. 104584
    Prev
    Next
    INDEX
    Explanations

    suffixes associated with personal names

    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
    blind
    -0.07
    rotation
    -0.07
    zano
    -0.07
    .scalablytyped
    -0.07
    'es
    -0.07
     plá
    -0.06
    thers
    -0.06
    utenberg
    -0.06
    à¹īà¸ĩ
    -0.06
    âng
    -0.06
    POSITIVE LOGITS
    razier
    0.07
    ılıç
    0.07
    icker
    0.07
    berman
    0.07
    alled
    0.07
    fy
    0.06
     pillar
    0.06
     Craig
    0.06
    ELL
    0.06
    onen
    0.06
    Activations Density 0.034%

    No Known Activations