© 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. 30510
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash

    This neuron fires on phrases describing someone’s residence situation—specifically “lives with [his/her] [family/partner/etc.]” statements.

    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
     EventArgs
    -0.07
    een
    -0.07
     wiring
    -0.07
     upp
    -0.07
    umm
    -0.06
     lãnh
    -0.06
    .ReadUInt
    -0.06
    ]==
    -0.06
    _fds
    -0.06
    هد
    -0.06
    POSITIVE LOGITS
    ชร
    0.07
     domicile
    0.06
    acak
    0.06
    antwort
    0.06
     moved
    0.06
     Residence
    0.06
    -times
    0.06
     philippines
    0.06
     residence
    0.06
     FAG
    0.06
    Activations Density 0.008%

    No Known Activations