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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126058
    Prev
    Next
    INDEX
    Explanations

    females

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of “Girls” or “Women’s” as part of group or event names, i.e. references to female-specific organizations or cohorts.

    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
     fonction
    -0.07
    ']},↵
    -0.07
    ()↵↵
    -0.07
    वत
    -0.07
     goodness
    -0.07
    554
    -0.07
    HD
    -0.07
    -key
    -0.07
    (range
    -0.07
    .magnitude
    -0.07
    POSITIVE LOGITS
     queues
    0.06
    	synchronized
    0.06
     nucle
    0.06
    localStorage
    0.06
    अ
    0.05
     PyObject
    0.05
    рія
    0.05
    っても
    0.05
     Floating
    0.05
     Superv
    0.05
    Activations Density 0.033%

    No Known Activations