© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52523
    Prev
    Next
    INDEX
    Explanations

    LIGO

    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
     communion
    -0.07
    	conn
    -0.07
    磁
    -0.06
     correction
    -0.06
     mater
    -0.06
    _unpack
    -0.06
    ujete
    -0.06
    /dat
    -0.06
    neighbor
    -0.06
     pert
    -0.06
    POSITIVE LOGITS
     perk
    0.07
    <!--<
    0.07
    EDIATEK
    0.06
     söz
    0.06
    QS
    0.06
     Extend
    0.06
    \""
    0.06
    Pod
    0.06
     touches
    0.06
    >'
    0.06
    Activations Density 0.004%

    No Known Activations