© 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. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58000
    Prev
    Next
    INDEX
    Explanations

    ulated

    np_max-act · gemini-2.0-flash

    The neuron activates on subwords of “modulated” (e.g. “mod,” “ulated,” “Intensity-modulated”)—in other words, it flags mentions of intensity‐modulated radiation therapy terminology.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     diary
    -0.07
     Floral
    -0.07
     affordable
    -0.06
    rát
    -0.06
     naopak
    -0.06
     pen
    -0.06
     Pony
    -0.06
     lies
    -0.06
     Salisbury
    -0.06
     Models
    -0.06
    POSITIVE LOGITS
    ott
    0.07
     byt
    0.06
     vv
    0.06
    	GLuint
    0.06
     Int
    0.06
     weakest
    0.06
    mounted
    0.06
    ��
    0.06
    ocrisy
    0.06
     کری
    0.06
    Activations Density 0.002%

    No Known Activations