© 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. 125187
    Prev
    Next
    INDEX
    Explanations

    top

    np_max-act · gemini-2.0-flash

    This neuron activates on the HTML “top” navigation element (e.g. the `<div id="top">` marker), i.e. it detects that specific structural tag in the document.

    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
     UIImage
    -0.07
    Workers
    -0.07
    _proc
    -0.06
    asa
    -0.06
    оза
    -0.06
     Quarry
    -0.06
     Loan
    -0.06
     loans
    -0.06
    _sets
    -0.06
     icmp
    -0.06
    POSITIVE LOGITS
    νω
    0.08
    _UNITS
    0.07
    ्ष
    0.07
     Kral
    0.06
     viscosity
    0.06
     numéro
    0.06
    Cover
    0.06
    ัวร
    0.06
     ช
    0.06
     выбор
    0.06
    Activations Density 0.000%

    No Known Activations