© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89630
    Prev
    Next
    INDEX
    Explanations

    "has", questions and problems

    np_max-act · gemini-2.0-flash

    The neuron fires on text asking whether one “has” or “is” afflicted by some problem or condition (e.g. addiction, being hacked).

    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
    	User
    -0.07
    uesto
    -0.07
     memor
    -0.07
    АН
    -0.07
     ثبت
    -0.07
     tránh
    -0.06
    іли
    -0.06
    ルド
    -0.06
    (payload
    -0.06
     perpetr
    -0.06
    POSITIVE LOGITS
    --------------
    0.07
    _videos
    0.07
     "/
    0.06
    TEMPL
    0.06
     gboolean
    0.06
    DetailsService
    0.06
     Westminster
    0.06
      ↵  ↵
    0.06
    %">↵
    0.06
     Delhi
    0.06
    Activations Density 0.029%

    No Known Activations