© 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. 89883
    Prev
    Next
    INDEX
    Explanations

    database and coding

    np_max-act · gemini-2.0-flash

    This neuron activates on SQL named‐parameter placeholders (tokens like “:paramName”) in prepared statements.

    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
    Observers
    -0.08
     Placement
    -0.08
    在线
    -0.07
    แนะ
    -0.07
    Planning
    -0.07
    >>>(
    -0.07
    Forgot
    -0.07
    rbrakk
    -0.06
    	Result
    -0.06
     advis
    -0.06
    POSITIVE LOGITS
    _Desc
    0.06
     including
    0.06
    _digit
    0.06
     ranging
    0.06
     Case
    0.06
    δο
    0.06
    lia
    0.06
    	dataType
    0.05
    ρό
    0.05
     мл
    0.05
    Activations Density 0.008%

    No Known Activations