© 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. 19191
    Prev
    Next
    INDEX
    Explanations

    Focus, on

    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
    قيق
    -0.07
     allies
    -0.07
    metrical
    -0.06
    Enabled
    -0.06
    روب
    -0.06
    zed
    -0.06
     数
    -0.06
    发现
    -0.06
     Avatar
    -0.06
    كام
    -0.06
    POSITIVE LOGITS
    ()][
    0.08
    =min
    0.06
    ()]
    0.06
     gir
    0.06
     umění
    0.06
     кни
    0.06
     Ali
    0.06
    ahkan
    0.06
    .spi
    0.06
     invit
    0.06
    Activations Density 0.050%

    No Known Activations