© 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. 3-RESID-POST-AA
    11. 123109
    Prev
    Next
    INDEX
    Explanations

    element

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    енно
    -0.06
    ۲۴
    -0.06
     vál
    -0.06
     causes
    -0.06
    _known
    -0.06
     assumptions
    -0.06
     atual
    -0.06
     FIT
    -0.06
     provisions
    -0.06
    _Status
    -0.05
    POSITIVE LOGITS
     element
    0.19
    Element
    0.16
     Element
    0.14
    element
    0.12
    -element
    0.11
    	element
    0.10
    	elem
    0.09
    .documentElement
    0.09
    _element
    0.09
    (element
    0.09
    Activations Density 0.025%

    No Known Activations