© 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
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 99177
    Prev
    Next
    INDEX
    Explanations

    formulas

    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
     antibiotics
    -0.07
    ávající
    -0.06
     hateful
    -0.06
     processo
    -0.06
    같은
    -0.06
    这个
    -0.06
     willen
    -0.06
    onse
    -0.06
    SBATCH
    -0.06
    hus
    -0.06
    POSITIVE LOGITS
     
    0.13
    [axis
    0.07
     Комп
    0.06
    بل
    0.06
    .setColumns
    0.06
     ACPI
    0.06
     outspoken
    0.06
    .hm
    0.06
     flam
    0.06
     
    0.06
    Activations Density 0.001%

    No Known Activations