© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8917
    Prev
    Next
    INDEX
    Explanations

    Dosage recommendations

    np_max-act · gemini-2.0-flash

    The neuron flags mentions of drug dosage instructions—numbers (e.g. “20” or “250”), units (mg, veces, por día), and related dosage-recommendation terms.

    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
    	Write
    -0.07
    924
    -0.06
    AP
    -0.06
    Defaults
    -0.06
     Yol
    -0.06
    /mark
    -0.06
     질문
    -0.06
    １０
    -0.06
     جهان
    -0.06
    045
    -0.05
    POSITIVE LOGITS
    employment
    0.08
    าจาก
    0.06
     ora
    0.06
    _SECONDS
    0.06
     вред
    0.06
     Rodgers
    0.06
     voleb
    0.06
    �
    0.06
    )));
    0.06
     프로그램
    0.06
    Activations Density 0.023%

    No Known Activations