© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 95382
    Prev
    Next
    INDEX
    Explanations

    K. pneumoniae bacteria

    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
                     
    -0.07
    criteria
    -0.07
     Kush
    -0.06
    .ImageView
    -0.06
     зак
    -0.06
    Formatting
    -0.06
    .addAction
    -0.06
     когда
    -0.06
    347
    -0.06
    >(*
    -0.06
    POSITIVE LOGITS
     mínimo
    0.06
     datum
    0.06
     Derm
    0.06
    esimal
    0.06
     špat
    0.06
    	command
    0.06
    �果
    0.06
    ))"↵
    0.06
    _gp
    0.06
    utters
    0.06
    Activations Density 0.106%

    No Known Activations