© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13180
    Prev
    Next
    INDEX
    Explanations

    Actions of removing, inserting, changing

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric quantities (especially decimal numbers and measurement values).

    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
     equivalents
    -0.07
    appId
    -0.07
    concat
    -0.06
    Plan
    -0.06
    createElement
    -0.06
    	var
    -0.06
     justification
    -0.06
    .degree
    -0.06
    Une
    -0.06
    846
    -0.06
    POSITIVE LOGITS
     Đảng
    0.07
     relocated
    0.07
    ("----------------
    0.07
     وت
    0.06
    ")]
↵
    0.06
    (TYPE
    0.06
     Kinect
    0.06
    EqualTo
    0.06
    /")↵
    0.06
     Profession
    0.06
    Activations Density 0.046%

    No Known Activations