© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95383
    Prev
    Next
    INDEX
    Explanations

    budget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rete
    -0.06
     en
    -0.06
     measure
    -0.06
     terminal
    -0.06
     Alexandre
    -0.06
    _tile
    -0.06
    apellido
    -0.06
     etter
    -0.06
    _accept
    -0.06
    .fa
    -0.06
    POSITIVE LOGITS
     budget
    0.21
     Budget
    0.20
     budgets
    0.15
    Budget
    0.13
    -budget
    0.12
     бюдж
    0.11
    budget
    0.11
    udget
    0.07
    _budget
    0.07
     Appropri
    0.07
    Activations Density 0.005%

    No Known Activations