© 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. 126664
    Prev
    Next
    INDEX
    Explanations

    magnet

    np_max-act · gemini-2.0-flash

    technical details related to magnetic devices and their applications.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron activates on occurrences of the root “magnet” (and its derivatives) in words.

    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
     surveillance
    -0.07
     BU
    -0.07
    ैय
    -0.07
     culinary
    -0.07
     RID
    -0.07
     chua
    -0.06
    iddle
    -0.06
    _done
    -0.06
     рос
    -0.06
    ission
    -0.06
    POSITIVE LOGITS
     magnet
    0.09
     Magnet
    0.09
    kt
    0.07
      ↵
    0.07
     Motors
    0.07
    agnet
    0.07
    ”↵
    0.07
     معت
    0.07
     PyQt
    0.07
     magnets
    0.07
    Activations Density 0.003%

    No Known Activations