© 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. 6892
    Prev
    Next
    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron detects references to the positions (first, second, third, etc.) of elements in tuple- or pair-structured data descriptions.

    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
    .Bind
    -0.07
    .Z
    -0.07
    397
    -0.07
     事
    -0.07
    Pal
    -0.06
    olves
    -0.06
    aju
    -0.06
     tribute
    -0.06
     endorsing
    -0.06
    rey
    -0.06
    POSITIVE LOGITS
     JAXB
    0.07
     mixin
    0.06
     花
    0.06
    (old
    0.06
    ฺ
    0.06
     Шев
    0.06
     جریان
    0.06
     CallingConvention
    0.06
     роки
    0.06
     suic
    0.06
    Activations Density 0.021%

    No Known Activations