© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 9141
    Prev
    Next
    INDEX
    Explanations

    Twitter handles, names

    np_max-act · gemini-2.0-flash

    This neuron lights up on personal names and handles in author bylines or social‐media links (e.g. author names and associated Twitter/URL fragments).

    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
     vectors
    -0.07
    quests
    -0.07
    uri
    -0.06
    Images
    -0.06
    arness
    -0.06
    ESA
    -0.06
     serde
    -0.06
    .Offset
    -0.06
     paradigm
    -0.06
     oversight
    -0.06
    POSITIVE LOGITS
     단
    0.07
     ")
↵
    0.06
     ومع
    0.06
    jected
    0.06
     แบบ
    0.06
    ):
    0.06
    ंड
    0.06
     misled
    0.06
    	unit
    0.06
    주의
    0.06
    Activations Density 0.021%

    No Known Activations