© 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. 57408
    Prev
    Next
    INDEX
    Explanations

    mod

    np_max-act · gemini-2.0-flash

    The neuron specifically fires on terms naming the malaria parasite (especially “Plasmodium”) and its life‐cycle stages (e.g. merozoites, sporozoites, erythrocytic, asexual, sexual).

    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
    .ByteArray
    -0.07
     Böylece
    -0.07
    /O
    -0.07
     kurs
    -0.07
     Rosenberg
    -0.07
     ConsoleColor
    -0.07
    -Type
    -0.07
    .trip
    -0.06
     カ
    -0.06
     CHUNK
    -0.06
    POSITIVE LOGITS
     може
    0.07
    그래
    0.07
     меди
    0.06
    -facing
    0.06
    macen
    0.06
     работ
    0.06
    ìm
    0.06
    帖
    0.06
    Spl
    0.06
     cé
    0.05
    Activations Density 0.004%

    No Known Activations