© 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. 96654
    Prev
    Next
    INDEX
    Explanations

    deliver

    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
    แม
    -0.07
    נ
    -0.07
    alf
    -0.07
     encyclopedia
    -0.06
    (pattern
    -0.06
    :["
    -0.06
     зави
    -0.06
    �
    -0.06
     eat
    -0.06
    oded
    -0.06
    POSITIVE LOGITS
     delivering
    0.07
     delivery
    0.07
    _each
    0.07
    elling
    0.07
    _TYPED
    0.06
    ایسه
    0.06
     Nir
    0.06
     gm
    0.06
    >Select
    0.06
     LB
    0.06
    Activations Density 0.009%

    No Known Activations