© 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. 41697
    Prev
    Next
    INDEX
    Explanations

    ic

    np_max-act · gemini-2.0-flash

    The neuron activates on the subword pieces (“al‐log‐ene‐ic,” “allo-H,” etc.) that compose the term “allogeneic,” i.e. references to allogeneic stem cell transplantation.

    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
     nurs
    -0.07
     вироб
    -0.07
     Spit
    -0.07
    nickname
    -0.06
     follic
    -0.06
     Extreme
    -0.06
     університ
    -0.06
    Strike
    -0.06
     percentage
    -0.06
     birthdays
    -0.06
    POSITIVE LOGITS
     seasoned
    0.08
    clientId
    0.07
     dej
    0.07
    .ordinal
    0.06
     glBind
    0.06
     extern
    0.06
     trẻ
    0.06
    →
    0.06
    银行
    0.06
     clr
    0.06
    Activations Density 0.002%

    No Known Activations