© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13524
    Prev
    Next
    INDEX
    Explanations

    OR

    np_max-act · gemini-2.0-flash

    This neuron fires on all-caps identifiers—i.e. constant or macro names composed of uppercase letters and underscores.

    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
    egrate
    -0.07
    JNIEXPORT
    -0.06
    folders
    -0.06
    ії
    -0.06
    _mpi
    -0.06
    _fire
    -0.06
     ACM
    -0.06
     dealer
    -0.06
     losses
    -0.06
    _kwargs
    -0.06
    POSITIVE LOGITS
    /on
    0.07
    μένο
    0.07
     Janeiro
    0.07
    _product
    0.06
     estaba
    0.06
    PreparedStatement
    0.06
    _keys
    0.06
    Brandon
    0.06
     topp
    0.06
     estava
    0.06
    Activations Density 0.024%

    No Known Activations