© 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. 15-RESID-POST-AA
    6. 12880
    Prev
    Next
    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nhĩ
    -0.07
    <Integer
    -0.07
    badge
    -0.07
    <Long
    -0.06
    όγ
    -0.06
     blatant
    -0.06
    ovice
    -0.06
     نگاه
    -0.06
     chocol
    -0.06
    lord
    -0.06
    POSITIVE LOGITS
    reatest
    0.06
    {}".
    0.06
     exam
    0.06
     Massachusetts
    0.06
    asurement
    0.06
     specially
    0.06
     atte
    0.06
    就会
    0.06
    �
    0.06
    	pre
    0.06
    Activations Density 0.010%

    No Known Activations