© 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
    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. 25227
    Prev
    Next
    INDEX
    Explanations

    licensed

    np_max-act · gemini-2.0-flash

    The neuron detects factual metadata about radio stations—especially licensing and ownership details (e.g. “licensed,” “owned,” call‐letter frequencies).

    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
    .Detail
    -0.07
    achines
    -0.07
    _DETECT
    -0.07
     zus
    -0.06
    (pd
    -0.06
    .Static
    -0.06
    patients
    -0.06
     Aust
    -0.06
     ایت
    -0.06
     Ví
    -0.06
    POSITIVE LOGITS
    Published
    0.07
     Holder
    0.06
     itemName
    0.06
     sessionStorage
    0.06
    良
    0.06
     Amendment
    0.06
     Mare
    0.06
    辞
    0.06
    .minecraft
    0.06
     %}↵
    0.06
    Activations Density 0.001%

    No Known Activations