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. 23-RESID-POST-AA
    6. 103865
    Prev
    Next
    INDEX
    Explanations

    specific manner

    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_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Writing
    -0.07
     writing
    -0.06
    -validate
    -0.06
    currentUser
    -0.06
     Positions
    -0.06
     whatsoever
    -0.06
     mutlaka
    -0.06
    вали
    -0.06
     pretending
    -0.06
     tienes
    -0.05
    POSITIVE LOGITS
     DAG
    0.07
     suppressed
    0.07
    OPT
    0.06
     slash
    0.06
    �
    0.06
     اط
    0.06
    оля
    0.06
     conse
    0.06
    _console
    0.06
    ANCEL
    0.06
    Activations Density 0.053%

    No Known Activations