© 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. 25066
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     speculative
    -0.07
     Βασ
    -0.07
     Hog
    -0.06
    ska
    -0.06
    .extern
    -0.06
     lum
    -0.06
    (LOG
    -0.06
    、高
    -0.06
     Diet
    -0.06
     extradition
    -0.06
    POSITIVE LOGITS
    .navCtrl
    0.06
     инвести
    0.06
    олнитель
    0.06
    форми
    0.06
    ków
    0.06
    (".")
    0.06
    }<
    0.06
    [out
    0.06
    _EXT
    0.06
    ζα
    0.06
    Activations Density 0.133%

    No Known Activations