© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 9126
    Prev
    Next
    INDEX
    Explanations

    Autobiographical stories, age referenced

    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
    hz
    -0.07
     خر
    -0.07
    دانلود
    -0.07
    خة
    -0.07
     examined
    -0.07
     فرانسه
    -0.07
     Rift
    -0.06
     Joyce
    -0.06
    نى
    -0.06
     tuner
    -0.06
    POSITIVE LOGITS
    .central
    0.06
    ıf
    0.05
     Entered
    0.05
    ?p
    0.05
    anking
    0.05
    divider
    0.05
     (�
    0.05
    ягом
    0.05
    undred
    0.05
     Grave
    0.05
    Activations Density 0.023%

    No Known Activations