Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30368
    Prev
    Next
    INDEX
    Explanations

    bending

    np_max-act · gemini-2.0-flash

    The neuron activates on terms describing mechanical stresses and deformations (e.g. bending, torsional, twisting, deflection).

    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
     Coverage
    -0.07
    .header
    -0.06
    ,target
    -0.06
     Archbishop
    -0.06
     asia
    -0.06
     CAMERA
    -0.06
     Ul
    -0.06
    10
    -0.06
    acağız
    -0.06
    (TYPE
    -0.06
    POSITIVE LOGITS
    ΑΡ
    0.07
    Buying
    0.06
    REDIS
    0.06
    َم
    0.06
     Ste
    0.06
     morals
    0.06
    Sex
    0.06
     motor
    0.06
     dragging
    0.06
    QUIT
    0.06
    Activations Density 0.005%

    No Known Activations