© 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. 15-RESID-POST-AA
    11. 114024
    Prev
    Next
    INDEX
    Explanations

    when

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EXPECT
    -0.06
    (note
    -0.06
    _manager
    -0.06
     quantify
    -0.06
     شب
    -0.06
     Mockito
    -0.06
    .initial
    -0.06
     vant
    -0.06
    Dimension
    -0.06
     RETURN
    -0.06
    POSITIVE LOGITS
    jury
    0.07
    ivot
    0.06
    ardır
    0.06
    Advertis
    0.06
     declaring
    0.06
     -,
    0.06
    (Canvas
    0.06
    (encoding
    0.06
    +(
    0.06
    ――
    0.06
    Activations Density 0.338%

    No Known Activations