© 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. 129605
    Prev
    Next
    INDEX
    Explanations

    _array

    np_max-act · gemini-2.0-flash

    This neuron fires on PHP MySQL row‐fetch calls (e.g. mysqli_fetch_array or mysqli_fetch_assoc).

    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
     Wit
    -0.06
     Identified
    -0.06
     Ted
    -0.06
     mother
    -0.06
     seek
    -0.06
     explanation
    -0.06
    وید
    -0.06
    :absolute
    -0.06
    \Service
    -0.06
     terrified
    -0.06
    POSITIVE LOGITS
    <Any
    0.07
    .syntax
    0.07
    ंध
    0.07
    ὐ
    0.06
    дром
    0.06
    -double
    0.06
    -ready
    0.06
    Different
    0.06
    <Int
    0.06
    835
    0.06
    Activations Density 0.000%

    No Known Activations