© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 56555
    Prev
    Next
    INDEX
    Explanations

    delimiters

    np_max-act · gemini-2.0-flash

    The neuron is detecting YAML “block scalar” lines—i.e. the `|` marker (and its indentation) that introduces multi‐line text in YAML documents.

    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
    Psych
    -0.07
    Nome
    -0.07
     klíč
    -0.06
    headline
    -0.06
    AUTH
    -0.06
     hallmark
    -0.06
    -service
    -0.06
    _loading
    -0.06
    /print
    -0.06
    ’app
    -0.06
    POSITIVE LOGITS
     &&↵
    0.07
    ữu
    0.06
    QQ
    0.06
    >()↵
    0.06
     quadr
    0.06
     sui
    0.06
    owego
    0.06
     victories
    0.06
    режд
    0.06
     жін
    0.06
    Activations Density 0.003%

    No Known Activations