© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91517
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of advisory or warning language, especially the word “important.”

    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
     starts
    -0.07
     почина
    -0.06
    Wr
    -0.06
    !');↵
    -0.06
    Within
    -0.06
    政策
    -0.06
    имо
    -0.06
    мы
    -0.06
    ací
    -0.06
    	utils
    -0.06
    POSITIVE LOGITS
    (bean
    0.07
     katıl
    0.07
    .Struct
    0.07
                                                                      
    0.07
                                                           
    0.07
    _TRAN
    0.07
    _TRY
    0.06
    <i
    0.06
    ,)
    0.06
    .now
    0.06
    Activations Density 0.015%

    No Known Activations