© 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. 19-RESID-POST-AA
    11. 35242
    Prev
    Next
    INDEX
    Explanations

    articles

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kenneth
    -0.07
     萬
    -0.07
     Meyer
    -0.07
     örgüt
    -0.07
     injector
    -0.07
     FOX
    -0.07
     CIA
    -0.07
     levy
    -0.06
     NEXT
    -0.06
    -carousel
    -0.06
    POSITIVE LOGITS
     shell
    0.06
    lášení
    0.06
    ct
    0.06
    ,id
    0.06
    ád
    0.06
     ='
    0.06
     dared
    0.06
    ()+
    0.06
    ETS
    0.05
    个人
    0.05
    Activations Density 0.141%

    No Known Activations