© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 53952
    Prev
    Next
    INDEX
    Explanations

    information

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ila
    -0.07
    >d
    -0.06
    olvable
    -0.06
     safe
    -0.06
    릴
    -0.06
    -at
    -0.06
     tec
    -0.06
    ;r
    -0.06
     Pell
    -0.06
    (bytes
    -0.06
    POSITIVE LOGITS
    	function
    0.07
    Young
    0.07
    ичний
    0.06
    (':
    0.06
     paramString
    0.06
    USES
    0.06
     Mourinho
    0.06
    ertility
    0.06
    итай
    0.06
     AudioManager
    0.06
    Activations Density 0.003%

    No Known Activations