© 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. 44276
    Prev
    Next
    INDEX
    Explanations

    actor transformation into roles

    np_max-act · gemini-2.0-flash

    The neuron lights up on imperative prompts telling the model to “immerse” itself into a specific role or persona.

    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
    \'
    -0.07
    *p
    -0.06
    vae
    -0.06
    _inverse
    -0.06
    XE
    -0.06
     também
    -0.06
     Forbes
    -0.06
    Fizz
    -0.06
     MacDonald
    -0.06
    	K
    -0.06
    POSITIVE LOGITS
     신규
    0.06
     cupid
    0.06
    Going
    0.06
    АН
    0.06
     اجازه
    0.06
     lanz
    0.06
    OURCE
    0.06
     nhận
    0.06
     Pub
    0.06
     laptop
    0.06
    Activations Density 0.003%

    No Known Activations