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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 129999
    Prev
    Next
    INDEX
    Explanations

    lation

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of “ablation,” especially in the context of radiofrequency ablation procedures.

    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
    녕하세요
    -0.06
     implications
    -0.06
    .parseColor
    -0.06
     paranoia
    -0.06
     PVOID
    -0.06
     RequestOptions
    -0.06
     workbook
    -0.06
    建設
    -0.06
    ोर
    -0.06
    보내기
    -0.06
    POSITIVE LOGITS
    kses
    0.07
     plum
    0.06
    .Strict
    0.06
    *c
    0.06
    .Audio
    0.06
     dispenser
    0.06
     ü
    0.06
    Grand
    0.06
     Todos
    0.06
     Plum
    0.06
    Activations Density 0.005%

    No Known Activations