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. 27-RESID-POST-AA
    6. 108932
    Prev
    Next
    INDEX
    Explanations

    say the ending -ent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .annotate
    -0.07
    Sup
    -0.06
    _Var
    -0.06
    /comment
    -0.06
    altitude
    -0.06
    objective
    -0.06
    Rx
    -0.06
     voor
    -0.06
     Carter
    -0.06
     oath
    -0.05
    POSITIVE LOGITS
     medio
    0.07
    idable
    0.07
    asyonu
    0.07
    CHandle
    0.07
     دسته
    0.07
     photography
    0.07
     gf
    0.06
    #\
    0.06
     groundbreaking
    0.06
     emiss
    0.06
    Activations Density 0.011%

    No Known Activations