© 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. 7-RESID-POST-AA
    11. 113649
    Prev
    Next
    INDEX
    Explanations

    de

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NECT
    -0.08
     보여
    -0.07
     عراق
    -0.07
    寺
    -0.07
    筒
    -0.06
    024
    -0.06
    ораз
    -0.06
     처리
    -0.06
     обнаруж
    -0.06
    toHaveBeenCalledWith
    -0.06
    POSITIVE LOGITS
    subscriber
    0.07
     půl
    0.06
    	Query
    0.06
    peak
    0.06
     Verm
    0.06
    OfBirth
    0.06
     همه
    0.06
    -fl
    0.06
     الحل
    0.06
     Camp
    0.06
    Activations Density 0.007%

    No Known Activations