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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 115193
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     severe
    -0.07
     वर
    -0.07
    归
    -0.06
     ماد
    -0.06
    675
    -0.06
    asures
    -0.06
    gist
    -0.06
     quần
    -0.06
    calar
    -0.06
     Hastings
    -0.06
    POSITIVE LOGITS
     symptom
    0.08
     loosely
    0.06
     Copyright
    0.06
          
↵
    0.06
    irement
    0.06
     tidy
    0.06
     assertThat
    0.06
     vb
    0.06
    CEEDED
    0.06
    getContext
    0.06
    Activations Density 0.060%

    No Known Activations