© 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. 42516
    Prev
    Next
    INDEX
    Explanations

    child abuse

    np_max-act · gemini-2.0-flash

    The neuron detects legal‐style mentions of child maltreatment (e.g. “child endangerment,” “abuse,” “neglect”) in court or case documents.

    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
    thickness
    -0.06
     sorumlu
    -0.06
     REPRESENT
    -0.06
    .case
    -0.06
     illusions
    -0.06
     unzip
    -0.06
     lite
    -0.06
     Regulation
    -0.06
    اب
    -0.06
    VERT
    -0.06
    POSITIVE LOGITS
     развити
    0.07
    SETTING
    0.07
    onestly
    0.07
     dah
    0.07
    ﾟ
    0.06
     Οι
    0.06
    Permanent
    0.06
     koji
    0.06
    еж
    0.06
    attered
    0.06
    Activations Density 0.014%

    No Known Activations