© 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. 90960
    Prev
    Next
    INDEX
    Explanations

    uri, prefix, lib

    np_max-act · gemini-2.0-flash

    This neuron detects JSP page and taglib directive elements (the `<%@ ... %>` declarations and their attributes).

    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
    GMT
    -0.07
     Tween
    -0.07
    DFS
    -0.07
    Inst
    -0.06
    enden
    -0.06
     구글상위
    -0.06
     shelter
    -0.06
    .Cond
    -0.06
    .Btn
    -0.06
     Surrey
    -0.06
    POSITIVE LOGITS
    hub
    0.07
     robbed
    0.06
     صنع
    0.06
     ConnectionState
    0.06
    _sk
    0.06
     περιο
    0.06
    abb
    0.06
    blings
    0.06
     policies
    0.06
     другой
    0.06
    Activations Density 0.004%

    No Known Activations