© 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. 23-RESID-POST-AA
    11. 7778
    Prev
    Next
    INDEX
    Explanations

    id/Amid

    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
     Browns
    -0.07
     Những
    -0.07
     Arrow
    -0.06
     rowData
    -0.06
    linha
    -0.06
     ny
    -0.06
    Ws
    -0.06
     động
    -0.06
     directed
    -0.06
    -cond
    -0.06
    POSITIVE LOGITS
    ]:
    0.06
    итися
    0.06
    STE
    0.06
    _FOLLOW
    0.06
    иц
    0.06
    ULT
    0.06
    (numpy
    0.05
    ){}↵
    0.05
     cleanliness
    0.05
     jScrollPane
    0.05
    Activations Density 0.004%

    No Known Activations