© 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. 88918
    Prev
    Next
    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash

    The neuron fires on metadata and credit phrases in video descriptions—tokens like “Video by,” “Filmed,” “Recorded on,” “Mastered by,” etc., that introduce production or attribution details.

    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
     iterations
    -0.07
    andoned
    -0.06
     halluc
    -0.06
    ін
    -0.06
     IPA
    -0.06
     footh
    -0.06
    ellen
    -0.06
     rulers
    -0.06
    .Dial
    -0.06
     yellow
    -0.06
    POSITIVE LOGITS
     تحت
    0.07
     režim
    0.07
     Futures
    0.07
    .useState
    0.07
    �다
    0.07
    北京
    0.07
    /*/
    0.07
    _episode
    0.06
    Modificar
    0.06
     oldukları
    0.06
    Activations Density 0.022%

    No Known Activations