© 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. 38136
    Prev
    Next
    INDEX
    Explanations

    uen

    np_max-act · gemini-2.0-flash

    The neuron is selectively activated by mentions of “influenza” (and its subwords) and related virus‐ or vaccine‐specific terms (e.g. virus, strain, H1N1).

    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
    getError
    -0.07
    др
    -0.06
     εφαρ
    -0.06
    eria
    -0.06
    ificacion
    -0.06
    pcion
    -0.06
     Manila
    -0.06
     Plymouth
    -0.06
    .Maybe
    -0.06
    iko
    -0.06
    POSITIVE LOGITS
     }};↵
    0.06
    Animated
    0.06
    Sch
    0.06
    "Don
    0.06
    aten
    0.06
     가진
    0.06
    -IN
    0.06
    se
    0.06
    /.
    0.06
     gained
    0.06
    Activations Density 0.001%

    No Known Activations