© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9315
    Prev
    Next
    INDEX
    Explanations

    PostgreSQL

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the PostgreSQL database name (e.g. “PostgreSQL,” “greSQL,” “gres,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    technical terms and features related to database management systems, particularly PostgreSQL.

    oai_token-act-pair · gpt-4o-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
     customized
    -0.07
    .memory
    -0.06
    	diff
    -0.06
    頻
    -0.06
    Rub
    -0.06
    emotion
    -0.06
     UUID
    -0.06
    _FORCE
    -0.06
    nextInt
    -0.06
    иль
    -0.06
    POSITIVE LOGITS
     PostgreSQL
    0.10
    pgsql
    0.08
    Regarding
    0.07
    ssql
    0.07
     Npgsql
    0.07
     Passive
    0.07
     �
    0.07
    gresql
    0.07
     сказал
    0.07
    leşme
    0.06
    Activations Density 0.004%

    No Known Activations