© 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. 15-RESID-POST-AA
    11. 39929
    Prev
    Next
    INDEX
    Explanations

    mathematical functions

    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
    _IDS
    -0.07
    _MAP
    -0.07
    Z
    -0.07
    |array
    -0.07
    bz
    -0.07
     timelines
    -0.06
     Partition
    -0.06
    _counter
    -0.06
    -secondary
    -0.06
    Awesome
    -0.06
    POSITIVE LOGITS
     hầu
    0.07
    怀
    0.07
     UIApplication
    0.06
     radicals
    0.06
     KUR
    0.06
     linestyle
    0.06
    plication
    0.06
    _configs
    0.06
    กรรม
    0.06
    uble
    0.06
    Activations Density 0.008%

    No Known Activations