© 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. 65237
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on tokens involved in assigning a value to a variable (i.e. the left‐hand side of “=” assignments).

    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
    CDF
    -0.07
    '↵↵↵↵
    -0.06
    και
    -0.06
    _F
    -0.06
    (operation
    -0.06
     vrouw
    -0.06
     Budd
    -0.06
     gatherings
    -0.06
     metav
    -0.06
     niece
    -0.06
    POSITIVE LOGITS
    ері
    0.06
    inho
    0.06
     Neville
    0.06
    ecial
    0.06
     conversation
    0.06
     Lantern
    0.06
    приєм
    0.06
     basin
    0.06
     جامعة
    0.06
    >-
    0.06
    Activations Density 0.089%

    No Known Activations