Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 25448
    Prev
    Next
    INDEX
    Explanations

    strict

    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
     valuable
    -0.07
    ��
    -0.07
     mike
    -0.06
     Pamela
    -0.06
    .isNullOrEmpty
    -0.06
     ViewModel
    -0.06
    ंज
    -0.06
     sabe
    -0.06
     puzzle
    -0.06
     Kle
    -0.06
    POSITIVE LOGITS
     strict
    0.14
     strictly
    0.11
     stricter
    0.11
     Strict
    0.10
    Strict
    0.10
     stringent
    0.09
    (strict
    0.08
     minOccurs
    0.08
    structor
    0.07
     STRICT
    0.07
    Activations Density 0.008%

    No Known Activations