© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 81010
    Prev
    Next
    INDEX
    Explanations

    parentheses

    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
     Wilde
    -0.07
    usually
    -0.07
    摸
    -0.06
    wrapped
    -0.06
    ัญช
    -0.06
     Pillow
    -0.06
    zet
    -0.06
    Todos
    -0.06
    Rock
    -0.06
    testing
    -0.06
    POSITIVE LOGITS
    (pt
    0.07
    	UINT
    0.07
    (float
    0.07
     indo
    0.07
     listop
    0.06
    (int
    0.06
    .std
    0.06
    ',[
    0.06
    	EXPECT
    0.06
    UIBarButtonItem
    0.06
    Activations Density 0.165%

    No Known Activations