© 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. 55485
    Prev
    Next
    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on fragments of digital object identifiers and URLs (e.g. the “10.1002/…”, “/clc.”, “/rcr.” style DOI/URL substrings).

    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
     바람
    -0.07
    (shell
    -0.07
    disc
    -0.06
    typings
    -0.06
    notation
    -0.06
     dataframe
    -0.06
     ps
    -0.06
    .tt
    -0.06
     conveyor
    -0.06
    menu
    -0.06
    POSITIVE LOGITS
     occupies
    0.07
    ітет
    0.07
     fairly
    0.07
     mighty
    0.07
     retirement
    0.06
    ियर
    0.06
    Margin
    0.06
    agenda
    0.06
     même
    0.06
     suing
    0.06
    Activations Density 0.004%

    No Known Activations