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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 58910
    Prev
    Next
    INDEX
    Explanations

    smartphone models and launches

    np_max-act · gemini-2.0-flash

    This neuron activates on smartphone product names—i.e. brand‐plus‐model identifiers (like “Reno 4 Series,” “Galaxy Note 20,” “Mi 6,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _case
    -0.06
    _geom
    -0.06
    -cr
    -0.06
    (total
    -0.06
    áty
    -0.06
     ê
    -0.06
     setColor
    -0.06
     mute
    -0.06
    jerne
    -0.06
    カル
    -0.05
    POSITIVE LOGITS
    pez
    0.07
     développement
    0.07
     zengin
    0.06
     Sai
    0.06
     nutshell
    0.06
    amı
    0.06
     dapat
    0.06
     замі
    0.06
    ưng
    0.06
    ?)↵↵
    0.06
    Activations Density 0.013%

    No Known Activations