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

    Neuronpedia

    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. 6005
    Prev
    Next
    INDEX
    Explanations

    settings

    np_max-act · gemini-2.0-flash

    The neuron spikes on occurrences of the word “settings” (in various code or text contexts).

    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
    яз
    -0.07
     minions
    -0.06
     активно
    -0.06
    illion
    -0.06
    @Test
    -0.06
    действ
    -0.06
    sdk
    -0.06
    cline
    -0.06
    .domain
    -0.06
    (username
    -0.06
    POSITIVE LOGITS
     PSI
    0.06
     корп
    0.06
     condensed
    0.06
    _SY
    0.06
     Capitol
    0.06
     selectable
    0.06
    rodu
    0.06
     shortened
    0.06
    emony
    0.06
     earthqu
    0.06
    Activations Density 0.013%

    No Known Activations