© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30669
    Prev
    Next
    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash

    The neuron activates on inline style attributes (e.g. `style="…"` declarations) containing numeric CSS/layout values in wiki-table or HTML markup.

    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
    keterangan
    -0.07
    شة
    -0.06
     तरफ
    -0.06
    nom
    -0.06
    ��
    -0.06
    aniu
    -0.06
    columnName
    -0.06
    .reset
    -0.06
    แนะ
    -0.06
    антаж
    -0.06
    POSITIVE LOGITS
     Met
    0.08
    plit
    0.07
     the
    0.07
    _SELECTED
    0.07
     workbook
    0.07
    _SelectedIndexChanged
    0.07
     suppressed
    0.07
    multiply
    0.07
    ordo
    0.06
     setLocation
    0.06
    Activations Density 0.001%

    No Known Activations