© 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. 54502
    Prev
    Next
    INDEX
    Explanations

    prompts related to filling out forms or providing personal information

    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
    ires
    -0.07
    idor
    -0.07
     Duy
    -0.06
    iç
    -0.06
     incid
    -0.06
    bers
    -0.06
    oslav
    -0.06
    -lined
    -0.06
    ointments
    -0.06
     world
    -0.06
    POSITIVE LOGITS
    åªĴ
    0.07
    rlen
    0.07
    æĢ§
    0.07
    Ïĥμα
    0.06
    егоÑĢ
    0.06
    меÑī
    0.06
    etype
    0.06
    ëĭĪìĬ¤
    0.06
    #End
    0.06
    edik
    0.06
    Activations Density 0.004%

    No Known Activations