© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7190
    Prev
    Next
    INDEX
    Explanations

    first book/film descriptions

    np_max-act · gemini-2.0-flash

    information about film directors and their achievements.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to mentions of an individual’s creative works (titles of books or films) along with details of their publication or awards.

    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
     jurors
    -0.07
     coma
    -0.07
     usr
    -0.07
    life
    -0.06
     electrodes
    -0.06
     traf
    -0.06
    	Action
    -0.06
     PLUGIN
    -0.06
     Sistem
    -0.06
    _rm
    -0.06
    POSITIVE LOGITS
     Shim
    0.07
     соз
    0.06
    092
    0.06
    う
    0.06
    Rev
    0.06
    agh
    0.06
     аж
    0.06
     Covered
    0.06
    inging
    0.06
    _est
    0.06
    Activations Density 0.047%

    No Known Activations