© 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. 15-RESID-POST-AA
    6. 90697
    Prev
    Next
    INDEX
    Explanations

    ide

    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
     retaliation
    -0.07
    item
    -0.06
     sowie
    -0.06
    Instead
    -0.06
     fuera
    -0.06
     convened
    -0.06
    better
    -0.06
    دری
    -0.06
     Task
    -0.06
    AUSE
    -0.06
    POSITIVE LOGITS
    .innerWidth
    0.07
     lineNumber
    0.07
     IllegalArgumentException
    0.07
    γραφ
    0.07
    _wifi
    0.06
    whereIn
    0.06
    _TER
    0.06
     jlong
    0.06
     glyphicon
    0.06
     gelir
    0.06
    Activations Density 0.085%

    No Known Activations