© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38597
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment words

    np_max-act · gemini-2.0-flash

    The neuron detects derogatory terms used to describe complainers or malingerers (e.g., “whiners,” “hypochondriacs,” “drug seekers”).

    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
    HDR
    -0.07
    az
    -0.06
    396
    -0.06
    ��
    -0.06
     вертик
    -0.06
     luxe
    -0.06
    notif
    -0.06
     onNext
    -0.06
    mployee
    -0.06
    _func
    -0.06
    POSITIVE LOGITS
    partner
    0.07
    olithic
    0.07
     dna
    0.06
     gather
    0.06
     advantage
    0.06
     dispersed
    0.06
     intent
    0.06
    姓名
    0.06
     entra
    0.06
    _EFFECT
    0.06
    Activations Density 0.063%

    No Known Activations