© 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
    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. 129936
    Prev
    Next
    INDEX
    Explanations

    aquarium

    np_max-act · gemini-2.0-flash

    The neuron activates on key aquarium hobby terms, such as “aquarium,” “reef,” “tank,” “coral,” and “saltwater,” i.e. domain-specific nouns relating to aquarium keeping.

    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
    MenuStrip
    -0.07
    939
    -0.07
     výše
    -0.06
     UIButton
    -0.06
    _fsm
    -0.06
     courteous
    -0.06
    944
    -0.06
     několik
    -0.06
     humanoid
    -0.06
    VERTISEMENT
    -0.06
    POSITIVE LOGITS
    eguard
    0.07
     crafts
    0.06
     seja
    0.06
     Leicester
    0.06
    ocation
    0.06
    orges
    0.06
    生き
    0.06
    POSE
    0.06
    /init
    0.06
    AssignableFrom
    0.06
    Activations Density 0.010%

    No Known Activations