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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56606
    Prev
    Next
    INDEX
    Explanations

    env

    np_max-act · gemini-2.0-flash

    This neuron detects references to loading or managing environment variables from a “.env” file (e.g. mentions of “env,” “file,” “dotenv,” etc.).

    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
     dcc
    -0.07
     descendants
    -0.07
    今
    -0.07
     total
    -0.06
    plets
    -0.06
     barcelona
    -0.06
    Idle
    -0.06
     Puzzle
    -0.06
     volley
    -0.06
     Latter
    -0.06
    POSITIVE LOGITS
     sincerely
    0.06
     enhancement
    0.06
     traitement
    0.06
     thịt
    0.06
     proficiency
    0.06
     mourning
    0.06
    ([(
    0.06
    νι
    0.06
    .modal
    0.06
    戲
    0.06
    Activations Density 0.008%

    No Known Activations