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. 10110
    Prev
    Next
    INDEX
    Explanations

    nationalities

    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
     textbook
    -0.07
     initiation
    -0.06
     STOP
    -0.06
     TAX
    -0.06
     row
    -0.06
     comparator
    -0.06
     waiver
    -0.06
     ACTIONS
    -0.06
     ahead
    -0.06
     CONTROL
    -0.06
    POSITIVE LOGITS
     Australian
    0.09
     Spanish
    0.09
     Scottish
    0.09
     Canadian
    0.08
    Australian
    0.08
     Norwegian
    0.08
    Canadian
    0.08
    ghan
    0.08
     British
    0.08
     Swiss
    0.08
    Activations Density 0.138%

    No Known Activations