© 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. 54373
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash

    This neuron responds to words describing the act or state of closing or securing something (e.g., “close,” “closed,” “closing,” “retracted”).

    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
    松
    -0.06
     acidic
    -0.06
    pción
    -0.06
    Ether
    -0.06
    องค
    -0.06
    _COLUMNS
    -0.06
    inq
    -0.06
    oun
    -0.06
     free
    -0.05
    weapon
    -0.05
    POSITIVE LOGITS
    	event
    0.07
     trabaj
    0.07
     заключ
    0.06
     Decl
    0.06
     zaháj
    0.06
     dựng
    0.06
     input
    0.06
     Dtype
    0.06
     maj
    0.06
    }".
    0.06
    Activations Density 0.036%

    No Known Activations