© 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. 7-RESID-POST-AA
    6. 108594
    Prev
    Next
    INDEX
    Explanations

    stalk

    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
    Polit
    -0.07
     ÜNİVERSİTESİ
    -0.07
       
    -0.07
    ivid
    -0.07
     visualize
    -0.07
    moil
    -0.06
    [,]
    -0.06
    	mv
    -0.06
    ись
    -0.06
    /console
    -0.06
    POSITIVE LOGITS
     stalking
    0.16
     stalk
    0.13
    alker
    0.09
     lurking
    0.08
     lur
    0.08
    stalk
    0.07
    har
    0.07
    크
    0.07
    facebook
    0.07
    arb
    0.06
    Activations Density 0.002%

    No Known Activations