© 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. 44188
    Prev
    Next
    INDEX
    Explanations

    process/action/change

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens representing decimal values (i.e. floating-point numbers).

    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
     car
    -0.07
    387
    -0.06
     prio
    -0.06
     feathers
    -0.06
    ुर
    -0.06
     Urs
    -0.06
     convent
    -0.06
    工
    -0.06
    	conf
    -0.06
    атели
    -0.06
    POSITIVE LOGITS
    unned
    0.07
     DI
    0.07
     europé
    0.06
     UD
    0.06
    де
    0.06
     Boehner
    0.06
    】,【
    0.06
     ROUND
    0.06
    ektir
    0.06
    Cx
    0.06
    Activations Density 0.149%

    No Known Activations