© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126225
    Prev
    Next
    INDEX
    Explanations

    confirming details

    np_max-act · gemini-2.0-flash

    This neuron detects words involved in a speaker offering or providing personal/account details (e.g., “give,” “my,” “information,” “account,” “number”).

    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
     catastrophe
    -0.07
     PAD
    -0.06
    كيل
    -0.06
     SA
    -0.06
     자유
    -0.06
     predatory
    -0.06
    atives
    -0.06
    ца
    -0.06
    277
    -0.06
     Мед
    -0.06
    POSITIVE LOGITS
     REPORT
    0.07
     XHTML
    0.07
    ueblo
    0.06
     Hayes
    0.06
    MERCHANTABILITY
    0.06
    _DIRECTORY
    0.06
     gboolean
    0.06
     dirent
    0.06
     recharge
    0.06
    Johnny
    0.06
    Activations Density 0.009%

    No Known Activations