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. 15-RESID-POST-AA
    6. 114287
    Prev
    Next
    INDEX
    Explanations

    Common English words

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maior
    -0.08
     Georgian
    -0.07
     Forge
    -0.06
    RAD
    -0.06
     directors
    -0.06
    requires
    -0.06
    .IsNull
    -0.06
     rampage
    -0.06
    Kick
    -0.06
    طر
    -0.06
    POSITIVE LOGITS
     ^=
    0.06
     أخ
    0.06
     TextStyle
    0.06
     مشکل
    0.06
    thead
    0.06
     Εκ
    0.06
     TextEditingController
    0.06
    =item
    0.05
    InputBorder
    0.05
    /--
    0.05
    Activations Density 0.026%

    No Known Activations