© 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
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 25043
    Prev
    Next
    INDEX
    Explanations

    formulation

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blood
    -0.07
    <Player
    -0.07
     Bike
    -0.06
     Deposit
    -0.06
     mesel
    -0.06
     constantly
    -0.06
    ていた
    -0.06
     значення
    -0.06
     реб
    -0.06
     pickerView
    -0.06
    POSITIVE LOGITS
     formulation
    0.11
     formulations
    0.09
    .AppendFormat
    0.07
    aram
    0.07
    interpreter
    0.07
    AntiForgeryToken
    0.07
    documentation
    0.07
    .tagName
    0.07
    igation
    0.06
    @RequestMapping
    0.06
    Activations Density 0.003%

    No Known Activations