© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30614
    Prev
    Next
    INDEX
    Explanations

    Models and pin-ups

    np_max-act · gemini-2.0-flash

    This neuron fires on mentions of “Page 3 model” (i.e. those tabloid-style references to models, such as “Page 3 model Samantha Fox”).

    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
     başladı
    -0.06
     Nodo
    -0.06
     viable
    -0.06
     쓰
    -0.06
    659
    -0.06
    rne
    -0.06
     سبز
    -0.06
    _MAP
    -0.06
    ош
    -0.06
     sniff
    -0.06
    POSITIVE LOGITS
     beauty
    0.07
    csr
    0.07
     &:
    0.07
     unconstitutional
    0.07
     extradition
    0.07
    filer
    0.06
    ihilation
    0.06
    Beauty
    0.06
    กร
    0.06
    ลำ
    0.06
    Activations Density 0.016%

    No Known Activations