© 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. 110222
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash

    The neuron fires on German separable‐verb phrases describing the character actually carrying out an action (e.g. “führt … aus”).

    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
    BO
    -0.07
    flutter
    -0.06
     Mexican
    -0.06
    sockets
    -0.06
    杯
    -0.06
     ارد
    -0.06
     deposit
    -0.06
    quivo
    -0.06
    ько
    -0.06
     forests
    -0.06
    POSITIVE LOGITS
    ـــ
    0.07
     investigate
    0.06
     BACKGROUND
    0.06
     Ý
    0.06
    gsub
    0.06
     Στα
    0.06
    Gl
    0.06
    ด
    0.06
     раза
    0.06
     Vest
    0.06
    Activations Density 0.010%

    No Known Activations