© 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. 11-RESID-POST-AA
    11. 76237
    Prev
    Next
    INDEX
    Explanations

    He

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Workbook
    -0.07
     orn
    -0.07
     visions
    -0.07
     discern
    -0.07
    -no
    -0.06
    moved
    -0.06
    _SH
    -0.06
     offs
    -0.06
    .Count
    -0.06
     studied
    -0.06
    POSITIVE LOGITS
     rond
    0.07
     geme
    0.07
    werk
    0.07
     verm
    0.07
    をつ
    0.06
    lbrace
    0.06
    wallet
    0.06
     tela
    0.06
     발
    0.06
     dresses
    0.06
    Activations Density 0.105%

    No Known Activations