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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 122989
    Prev
    Next
    INDEX
    Explanations

    :

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rounded
    -0.07
     chicken
    -0.06
     live
    -0.06
     combining
    -0.06
     CARE
    -0.06
     Laptop
    -0.06
     squared
    -0.06
     π
    -0.06
     leur
    -0.06
     bé
    -0.06
    POSITIVE LOGITS
     Pratt
    0.14
     QtGui
    0.11
     QtWidgets
    0.11
    (LayoutInflater
    0.08
     Gaz
    0.07
    .textLabel
    0.07
    .:.:.:.
    0.07
     तत
    0.07
    علام
    0.06
    _PT
    0.06
    Activations Density 0.002%

    No Known Activations