© 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. 7-RESID-POST-AA
    6. 30344
    Prev
    Next
    INDEX
    Explanations

    á

    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
     componente
    -0.07
    ("[%
    -0.06
    $total
    -0.06
    “
    -0.06
    "...
    -0.06
    ा↵
    -0.06
    iedades
    -0.06
    <Item
    -0.06
    utable
    -0.06
     "\"
    -0.06
    POSITIVE LOGITS
     Pare
    0.06
    cob
    0.06
     JAXBElement
    0.06
    AGMA
    0.06
     componentWillMount
    0.06
     �
    0.06
    -character
    0.06
    (JS
    0.06
     خوش
    0.06
    ulmuş
    0.06
    Activations Density 0.299%

    No Known Activations