© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 21212
    Prev
    Next
    INDEX
    Explanations

    gene

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    因
    -0.07
    ัดการ
    -0.07
    ายน
    -0.07
    .Name
    -0.06
    .FloatField
    -0.06
     іс
    -0.06
    ísto
    -0.06
    (NUM
    -0.06
    lace
    -0.06
    styleType
    -0.06
    POSITIVE LOGITS
     mực
    0.07
    084
    0.06
    184
    0.06
    .aw
    0.06
    τικ
    0.06
     yüksel
    0.06
     Screw
    0.06
     shoe
    0.06
    �
    0.06
     sera
    0.06
    Activations Density 0.005%

    No Known Activations