© 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. 109477
    Prev
    Next
    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that give form cues—especially instructions to “keep/keeping your … straight,” “your back,” “body,” etc., i.e. posture‐and‐alignment guidance.

    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
    Levels
    -0.06
    ieved
    -0.06
    (_)
    -0.06
    /tags
    -0.06
    decltype
    -0.06
    「……
    -0.06
    emes
    -0.06
    给
    -0.06
    اصل
    -0.06
    еви
    -0.06
    POSITIVE LOGITS
    บาท
    0.07
    _attach
    0.07
    JKLMNOP
    0.07
    -shared
    0.06
     Electronic
    0.06
     knitting
    0.06
     famil
    0.06
    _bet
    0.06
     flatt
    0.06
     Fairfield
    0.06
    Activations Density 0.008%

    No Known Activations