© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 128792
    Prev
    Next
    INDEX
    Explanations

    code copyright

    np_max-act · gemini-2.0-flash

    license-related terminology and references.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects the opening banner lines of block comments—those long “/****…****/” separators at the top of source files.

    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
    rots
    -0.08
     Kr
    -0.07
     SYMBOL
    -0.07
       
    -0.07
    antiago
    -0.07
     deep
    -0.07
     Sand
    -0.07
     vc
    -0.07
     Dut
    -0.06
    dfs
    -0.06
    POSITIVE LOGITS
    /*******************************************************************************↵
    0.16
     NSArray
    0.06
    .dashboard
    0.06
    済
    0.06
     herb
    0.06
     佛
    0.06
    .getFile
    0.05
     Chester
    0.05
    bsd
    0.05
    _RECE
    0.05
    Activations Density 0.000%

    No Known Activations