© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89880
    Prev
    Next
    INDEX
    Explanations

    movement

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of statistical figures or numeric demographic data (e.g., population loss, numbers of residents moved).

    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
    .exe
    -0.07
    _parents
    -0.07
     petition
    -0.06
    %
    -0.06
    環
    -0.06
     Developer
    -0.06
     Volume
    -0.06
     panties
    -0.06
    _war
    -0.06
    Finish
    -0.06
    POSITIVE LOGITS
     immigr
    0.07
     شی
    0.07
    fas
    0.06
    Until
    0.06
     postupně
    0.06
    ermint
    0.06
    .src
    0.06
    .frequency
    0.06
     모델
    0.06
     automat
    0.06
    Activations Density 0.015%

    No Known Activations