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. 73087
    Prev
    Next
    INDEX
    Explanations

    Software/file allocation

    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
    隊
    -0.07
    iado
    -0.07
    ModelIndex
    -0.06
     retrie
    -0.06
    不可
    -0.06
     canal
    -0.06
    hours
    -0.06
    guna
    -0.06
     antim
    -0.06
     deliberate
    -0.06
    POSITIVE LOGITS
     ook
    0.07
    �
    0.07
    amsung
    0.07
     ภาษ
    0.07
    ões
    0.06
     libert
    0.06
     σχέ
    0.06
     projev
    0.06
    ão
    0.06
     Comm
    0.06
    Activations Density 0.100%

    No Known Activations